linux/drivers/net/macvlan.c

1663 lines
41 KiB
C
Raw Normal View History

/*
* Copyright (c) 2007 Patrick McHardy <kaber@trash.net>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
* published by the Free Software Foundation; either version 2 of
* the License, or (at your option) any later version.
*
* The code this is based on carried the following copyright notice:
* ---
* (C) Copyright 2001-2006
* Alex Zeffertt, Cambridge Broadband Ltd, ajz@cambridgebroadband.com
* Re-worked by Ben Greear <greearb@candelatech.com>
* ---
*/
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/rculist.h>
#include <linux/notifier.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/ethtool.h>
#include <linux/if_arp.h>
#include <linux/if_vlan.h>
#include <linux/if_link.h>
#include <linux/if_macvlan.h>
#include <linux/hash.h>
#include <linux/workqueue.h>
#include <net/rtnetlink.h>
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 14:07:10 +08:00
#include <net/xfrm.h>
#include <linux/netpoll.h>
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
#define MACVLAN_HASH_BITS 8
#define MACVLAN_HASH_SIZE (1<<MACVLAN_HASH_BITS)
#define MACVLAN_BC_QUEUE_LEN 1000
struct macvlan_port {
struct net_device *dev;
struct hlist_head vlan_hash[MACVLAN_HASH_SIZE];
struct list_head vlans;
struct sk_buff_head bc_queue;
struct work_struct bc_work;
bool passthru;
Revert "macvlan: simplify the structure port" This reverts commit a188a54d11629bef2169052297e61f3767ca8ce5. It causes crashes ==================== [ 80.643286] BUG: unable to handle kernel NULL pointer dereference at 0000000000000878 [ 80.670103] IP: [<ffffffff810832e4>] try_to_grab_pending+0x64/0x1f0 [ 80.691289] PGD 22c102067 PUD 235bf0067 PMD 0 [ 80.706611] Oops: 0002 [#1] SMP [ 80.717836] Modules linked in: macvlan nfsd lockd nfs_acl exportfs auth_rpcgss sunrpc oid_registry ioatdma ixgbe(-) mdio igb dca [ 80.757935] CPU: 37 PID: 6724 Comm: rmmod Not tainted 3.16.0-net-next-08-12-2014-FCoE+ #1 [ 80.785688] Hardware name: Intel Corporation S2600CO/S2600CO, BIOS SE5C600.86B.02.03.0003.041920141333 04/19/2014 [ 80.820310] task: ffff880235a9eae0 ti: ffff88022e844000 task.ti: ffff88022e844000 [ 80.845770] RIP: 0010:[<ffffffff810832e4>] [<ffffffff810832e4>] try_to_grab_pending+0x64/0x1f0 [ 80.875326] RSP: 0018:ffff88022e847b28 EFLAGS: 00010046 [ 80.893251] RAX: 0000000000037a6a RBX: 0000000000000878 RCX: 0000000000000000 [ 80.917187] RDX: ffff880235a9eae0 RSI: 0000000000000001 RDI: ffffffff810832db [ 80.941125] RBP: ffff88022e847b58 R08: 0000000000000000 R09: 0000000000000000 [ 80.965056] R10: 0000000000000001 R11: 0000000000000001 R12: ffff88022e847b70 [ 80.988994] R13: 0000000000000000 R14: ffff88022e847be8 R15: ffffffff81ebe440 [ 81.012929] FS: 00007fab90b07700(0000) GS:ffff88043f7a0000(0000) knlGS:0000000000000000 [ 81.040400] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 81.059757] CR2: 0000000000000878 CR3: 0000000235a42000 CR4: 00000000001407e0 [ 81.083689] Stack: [ 81.090739] ffff880235a9eae0 0000000000000878 ffff88022e847b70 0000000000000000 [ 81.116253] ffff88022e847be8 ffffffff81ebe440 ffff88022e847b98 ffffffff810847f1 [ 81.141766] ffff88022e847b78 0000000000000286 ffff880234200000 0000000000000000 [ 81.167282] Call Trace: [ 81.175768] [<ffffffff810847f1>] __cancel_work_timer+0x31/0x170 [ 81.195985] [<ffffffff8108494b>] cancel_work_sync+0xb/0x10 [ 81.214769] [<ffffffffa015ae68>] macvlan_port_destroy+0x28/0x60 [macvlan] [ 81.237844] [<ffffffffa015b930>] macvlan_uninit+0x40/0x50 [macvlan] [ 81.259209] [<ffffffff816bf6e2>] rollback_registered_many+0x1a2/0x2c0 [ 81.281140] [<ffffffff816bf81a>] unregister_netdevice_many+0x1a/0xb0 [ 81.302786] [<ffffffffa015a4ff>] macvlan_device_event+0x1ef/0x240 [macvlan] [ 81.326439] [<ffffffff8108a13d>] notifier_call_chain+0x4d/0x70 [ 81.346366] [<ffffffff8108a201>] raw_notifier_call_chain+0x11/0x20 [ 81.367439] [<ffffffff816bf25b>] call_netdevice_notifiers_info+0x3b/0x70 [ 81.390228] [<ffffffff816bf2a1>] call_netdevice_notifiers+0x11/0x20 [ 81.411587] [<ffffffff816bf6bd>] rollback_registered_many+0x17d/0x2c0 [ 81.433518] [<ffffffff816bf925>] unregister_netdevice_queue+0x75/0x110 [ 81.455735] [<ffffffff816bfb2b>] unregister_netdev+0x1b/0x30 [ 81.475094] [<ffffffffa0039b50>] ixgbe_remove+0x170/0x1d0 [ixgbe] [ 81.495886] [<ffffffff813512a2>] pci_device_remove+0x32/0x60 [ 81.515246] [<ffffffff814c75c4>] __device_release_driver+0x64/0xd0 [ 81.536321] [<ffffffff814c76f8>] driver_detach+0xc8/0xd0 [ 81.554530] [<ffffffff814c656e>] bus_remove_driver+0x4e/0xa0 [ 81.573888] [<ffffffff814c828b>] driver_unregister+0x2b/0x60 [ 81.593246] [<ffffffff8135143e>] pci_unregister_driver+0x1e/0xa0 [ 81.613749] [<ffffffffa005db18>] ixgbe_exit_module+0x1c/0x2e [ixgbe] [ 81.635401] [<ffffffff810e738b>] SyS_delete_module+0x15b/0x1e0 [ 81.655334] [<ffffffff8187a395>] ? sysret_check+0x22/0x5d [ 81.673833] [<ffffffff810abd2d>] ? trace_hardirqs_on_caller+0x11d/0x1e0 [ 81.696339] [<ffffffff8132bfde>] ? trace_hardirqs_on_thunk+0x3a/0x3f [ 81.717985] [<ffffffff8187a369>] system_call_fastpath+0x16/0x1b [ 81.738199] Code: 00 48 83 3d 6e bb da 00 00 48 89 c2 0f 84 67 01 00 00 fa 66 0f 1f 44 00 00 49 89 14 24 e8 b5 4b 02 00 45 84 ed 0f 85 ac 00 00 00 <f0> 0f ba 2b 00 72 1d 31 c0 48 8b 5d d8 4c 8b 65 e0 4c 8b 6d e8 [ 81.807026] RIP [<ffffffff810832e4>] try_to_grab_pending+0x64/0x1f0 [ 81.828468] RSP <ffff88022e847b28> [ 81.840384] CR2: 0000000000000878 [ 81.851731] ---[ end trace 9f6c7232e3464e11 ]--- ==================== This bug could be triggered by these steps: modprobe ixgbe ; modprobe macvlan ip link add link p96p1 address 00:1B:21:6E:06:00 macvlan0 type macvlan ip link add link p96p1 address 00:1B:21:6E:06:01 macvlan1 type macvlan ip link add link p96p1 address 00:1B:21:6E:06:02 macvlan2 type macvlan ip link add link p96p1 address 00:1B:21:6E:06:03 macvlan3 type macvlan rmmod ixgbe Reported-by: "Keller, Jacob E" <jacob.e.keller@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-08-15 05:32:49 +08:00
int count;
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
struct hlist_head vlan_source_hash[MACVLAN_HASH_SIZE];
DECLARE_BITMAP(mc_filter, MACVLAN_MC_FILTER_SZ);
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
};
struct macvlan_source_entry {
struct hlist_node hlist;
struct macvlan_dev *vlan;
unsigned char addr[6+2] __aligned(sizeof(u16));
struct rcu_head rcu;
};
struct macvlan_skb_cb {
const struct macvlan_dev *src;
};
#define MACVLAN_SKB_CB(__skb) ((struct macvlan_skb_cb *)&((__skb)->cb[0]))
static void macvlan_port_destroy(struct net_device *dev);
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
/* Hash Ethernet address */
static u32 macvlan_eth_hash(const unsigned char *addr)
{
u64 value = get_unaligned((u64 *)addr);
/* only want 6 bytes */
#ifdef __BIG_ENDIAN
value >>= 16;
#else
value <<= 16;
#endif
return hash_64(value, MACVLAN_HASH_BITS);
}
static struct macvlan_port *macvlan_port_get_rcu(const struct net_device *dev)
{
return rcu_dereference(dev->rx_handler_data);
}
static struct macvlan_port *macvlan_port_get_rtnl(const struct net_device *dev)
{
return rtnl_dereference(dev->rx_handler_data);
}
#define macvlan_port_exists(dev) (dev->priv_flags & IFF_MACVLAN_PORT)
static struct macvlan_dev *macvlan_hash_lookup(const struct macvlan_port *port,
const unsigned char *addr)
{
struct macvlan_dev *vlan;
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
u32 idx = macvlan_eth_hash(addr);
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
hlist_for_each_entry_rcu(vlan, &port->vlan_hash[idx], hlist) {
if (ether_addr_equal_64bits(vlan->dev->dev_addr, addr))
return vlan;
}
return NULL;
}
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
static struct macvlan_source_entry *macvlan_hash_lookup_source(
const struct macvlan_dev *vlan,
const unsigned char *addr)
{
struct macvlan_source_entry *entry;
u32 idx = macvlan_eth_hash(addr);
struct hlist_head *h = &vlan->port->vlan_source_hash[idx];
hlist_for_each_entry_rcu(entry, h, hlist) {
if (ether_addr_equal_64bits(entry->addr, addr) &&
entry->vlan == vlan)
return entry;
}
return NULL;
}
static int macvlan_hash_add_source(struct macvlan_dev *vlan,
const unsigned char *addr)
{
struct macvlan_port *port = vlan->port;
struct macvlan_source_entry *entry;
struct hlist_head *h;
entry = macvlan_hash_lookup_source(vlan, addr);
if (entry)
return 0;
entry = kmalloc(sizeof(*entry), GFP_KERNEL);
if (!entry)
return -ENOMEM;
ether_addr_copy(entry->addr, addr);
entry->vlan = vlan;
h = &port->vlan_source_hash[macvlan_eth_hash(addr)];
hlist_add_head_rcu(&entry->hlist, h);
vlan->macaddr_count++;
return 0;
}
static void macvlan_hash_add(struct macvlan_dev *vlan)
{
struct macvlan_port *port = vlan->port;
const unsigned char *addr = vlan->dev->dev_addr;
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
u32 idx = macvlan_eth_hash(addr);
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
hlist_add_head_rcu(&vlan->hlist, &port->vlan_hash[idx]);
}
static void macvlan_hash_del_source(struct macvlan_source_entry *entry)
{
hlist_del_rcu(&entry->hlist);
kfree_rcu(entry, rcu);
}
static void macvlan_hash_del(struct macvlan_dev *vlan, bool sync)
{
hlist_del_rcu(&vlan->hlist);
if (sync)
synchronize_rcu();
}
static void macvlan_hash_change_addr(struct macvlan_dev *vlan,
const unsigned char *addr)
{
macvlan_hash_del(vlan, true);
/* Now that we are unhashed it is safe to change the device
* address without confusing packet delivery.
*/
memcpy(vlan->dev->dev_addr, addr, ETH_ALEN);
macvlan_hash_add(vlan);
}
static bool macvlan_addr_busy(const struct macvlan_port *port,
const unsigned char *addr)
{
/* Test to see if the specified multicast address is
* currently in use by the underlying device or
* another macvlan.
*/
if (ether_addr_equal_64bits(port->dev->dev_addr, addr))
return true;
if (macvlan_hash_lookup(port, addr))
return true;
return false;
}
static int macvlan_broadcast_one(struct sk_buff *skb,
const struct macvlan_dev *vlan,
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 14:07:10 +08:00
const struct ethhdr *eth, bool local)
{
struct net_device *dev = vlan->dev;
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 14:07:10 +08:00
if (local)
return __dev_forward_skb(dev, skb);
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 14:07:10 +08:00
skb->dev = dev;
if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast))
skb->pkt_type = PACKET_BROADCAST;
else
skb->pkt_type = PACKET_MULTICAST;
return 0;
}
static u32 macvlan_hash_mix(const struct macvlan_dev *vlan)
{
return (u32)(((unsigned long)vlan) >> L1_CACHE_SHIFT);
}
static unsigned int mc_hash(const struct macvlan_dev *vlan,
const unsigned char *addr)
{
u32 val = __get_unaligned_cpu32(addr + 2);
val ^= macvlan_hash_mix(vlan);
return hash_32(val, MACVLAN_MC_FILTER_BITS);
}
static void macvlan_broadcast(struct sk_buff *skb,
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 14:07:10 +08:00
const struct macvlan_port *port,
struct net_device *src,
enum macvlan_mode mode)
{
const struct ethhdr *eth = eth_hdr(skb);
const struct macvlan_dev *vlan;
struct sk_buff *nskb;
unsigned int i;
int err;
unsigned int hash;
if (skb->protocol == htons(ETH_P_PAUSE))
return;
for (i = 0; i < MACVLAN_HASH_SIZE; i++) {
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:06:00 +08:00
hlist_for_each_entry_rcu(vlan, &port->vlan_hash[i], hlist) {
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 14:07:10 +08:00
if (vlan->dev == src || !(vlan->mode & mode))
continue;
hash = mc_hash(vlan, eth->h_dest);
if (!test_bit(hash, vlan->mc_filter))
continue;
err = NET_RX_DROP;
nskb = skb_clone(skb, GFP_ATOMIC);
if (likely(nskb))
err = macvlan_broadcast_one(
nskb, vlan, eth,
mode == MACVLAN_MODE_BRIDGE) ?:
netif_rx_ni(nskb);
macvlan_count_rx(vlan, skb->len + ETH_HLEN,
err == NET_RX_SUCCESS, true);
}
}
}
static void macvlan_process_broadcast(struct work_struct *w)
{
struct macvlan_port *port = container_of(w, struct macvlan_port,
bc_work);
struct sk_buff *skb;
struct sk_buff_head list;
__skb_queue_head_init(&list);
spin_lock_bh(&port->bc_queue.lock);
skb_queue_splice_tail_init(&port->bc_queue, &list);
spin_unlock_bh(&port->bc_queue.lock);
while ((skb = __skb_dequeue(&list))) {
const struct macvlan_dev *src = MACVLAN_SKB_CB(skb)->src;
rcu_read_lock();
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 14:07:10 +08:00
if (!src)
/* frame comes from an external address */
macvlan_broadcast(skb, port, NULL,
MACVLAN_MODE_PRIVATE |
MACVLAN_MODE_VEPA |
MACVLAN_MODE_PASSTHRU|
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 14:07:10 +08:00
MACVLAN_MODE_BRIDGE);
else if (src->mode == MACVLAN_MODE_VEPA)
/* flood to everyone except source */
macvlan_broadcast(skb, port, src->dev,
MACVLAN_MODE_VEPA |
MACVLAN_MODE_BRIDGE);
else
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 14:07:10 +08:00
/*
* flood only to VEPA ports, bridge ports
* already saw the frame on the way out.
*/
macvlan_broadcast(skb, port, src->dev,
MACVLAN_MODE_VEPA);
rcu_read_unlock();
if (src)
dev_put(src->dev);
kfree_skb(skb);
}
}
static void macvlan_broadcast_enqueue(struct macvlan_port *port,
const struct macvlan_dev *src,
struct sk_buff *skb)
{
struct sk_buff *nskb;
int err = -ENOMEM;
nskb = skb_clone(skb, GFP_ATOMIC);
if (!nskb)
goto err;
MACVLAN_SKB_CB(nskb)->src = src;
spin_lock(&port->bc_queue.lock);
if (skb_queue_len(&port->bc_queue) < MACVLAN_BC_QUEUE_LEN) {
if (src)
dev_hold(src->dev);
__skb_queue_tail(&port->bc_queue, nskb);
err = 0;
}
spin_unlock(&port->bc_queue.lock);
if (err)
goto free_nskb;
schedule_work(&port->bc_work);
return;
free_nskb:
kfree_skb(nskb);
err:
atomic_long_inc(&skb->dev->rx_dropped);
}
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
static void macvlan_flush_sources(struct macvlan_port *port,
struct macvlan_dev *vlan)
{
int i;
for (i = 0; i < MACVLAN_HASH_SIZE; i++) {
struct hlist_node *h, *n;
hlist_for_each_safe(h, n, &port->vlan_source_hash[i]) {
struct macvlan_source_entry *entry;
entry = hlist_entry(h, struct macvlan_source_entry,
hlist);
if (entry->vlan == vlan)
macvlan_hash_del_source(entry);
}
}
vlan->macaddr_count = 0;
}
static void macvlan_forward_source_one(struct sk_buff *skb,
struct macvlan_dev *vlan)
{
struct sk_buff *nskb;
struct net_device *dev;
int len;
int ret;
dev = vlan->dev;
if (unlikely(!(dev->flags & IFF_UP)))
return;
nskb = skb_clone(skb, GFP_ATOMIC);
if (!nskb)
return;
len = nskb->len + ETH_HLEN;
nskb->dev = dev;
nskb->pkt_type = PACKET_HOST;
ret = netif_rx(nskb);
macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, false);
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
}
static void macvlan_forward_source(struct sk_buff *skb,
struct macvlan_port *port,
const unsigned char *addr)
{
struct macvlan_source_entry *entry;
u32 idx = macvlan_eth_hash(addr);
struct hlist_head *h = &port->vlan_source_hash[idx];
hlist_for_each_entry_rcu(entry, h, hlist) {
if (ether_addr_equal_64bits(entry->addr, addr))
macvlan_forward_source_one(skb, entry->vlan);
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
}
}
/* called under rcu_read_lock() from netif_receive_skb */
static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb)
{
struct macvlan_port *port;
struct sk_buff *skb = *pskb;
const struct ethhdr *eth = eth_hdr(skb);
const struct macvlan_dev *vlan;
const struct macvlan_dev *src;
struct net_device *dev;
unsigned int len = 0;
int ret;
rx_handler_result_t handle_res;
port = macvlan_port_get_rcu(skb->dev);
if (is_multicast_ether_addr(eth->h_dest)) {
unsigned int hash;
skb = ip_check_defrag(dev_net(skb->dev), skb, IP_DEFRAG_MACVLAN);
if (!skb)
return RX_HANDLER_CONSUMED;
*pskb = skb;
eth = eth_hdr(skb);
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
macvlan_forward_source(skb, port, eth->h_source);
src = macvlan_hash_lookup(port, eth->h_source);
if (src && src->mode != MACVLAN_MODE_VEPA &&
src->mode != MACVLAN_MODE_BRIDGE) {
/* forward to original port. */
vlan = src;
ret = macvlan_broadcast_one(skb, vlan, eth, 0) ?:
netif_rx(skb);
handle_res = RX_HANDLER_CONSUMED;
goto out;
}
hash = mc_hash(NULL, eth->h_dest);
if (test_bit(hash, port->mc_filter))
macvlan_broadcast_enqueue(port, src, skb);
return RX_HANDLER_PASS;
}
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
macvlan_forward_source(skb, port, eth->h_source);
if (port->passthru)
vlan = list_first_or_null_rcu(&port->vlans,
struct macvlan_dev, list);
else
vlan = macvlan_hash_lookup(port, eth->h_dest);
if (vlan == NULL)
return RX_HANDLER_PASS;
dev = vlan->dev;
if (unlikely(!(dev->flags & IFF_UP))) {
kfree_skb(skb);
return RX_HANDLER_CONSUMED;
}
len = skb->len + ETH_HLEN;
skb = skb_share_check(skb, GFP_ATOMIC);
if (!skb) {
ret = NET_RX_DROP;
handle_res = RX_HANDLER_CONSUMED;
goto out;
}
*pskb = skb;
skb->dev = dev;
skb->pkt_type = PACKET_HOST;
ret = NET_RX_SUCCESS;
handle_res = RX_HANDLER_ANOTHER;
out:
macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, false);
return handle_res;
}
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 14:07:10 +08:00
static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
{
const struct macvlan_dev *vlan = netdev_priv(dev);
const struct macvlan_port *port = vlan->port;
const struct macvlan_dev *dest;
if (vlan->mode == MACVLAN_MODE_BRIDGE) {
const struct ethhdr *eth = (void *)skb->data;
/* send to other bridge ports directly */
if (is_multicast_ether_addr(eth->h_dest)) {
macvlan_broadcast(skb, port, dev, MACVLAN_MODE_BRIDGE);
goto xmit_world;
}
dest = macvlan_hash_lookup(port, eth->h_dest);
if (dest && dest->mode == MACVLAN_MODE_BRIDGE) {
/* send to lowerdev first for its network taps */
dev_forward_skb(vlan->lowerdev, skb);
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 14:07:10 +08:00
return NET_XMIT_SUCCESS;
}
}
xmit_world:
skb->dev = vlan->lowerdev;
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 14:07:10 +08:00
return dev_queue_xmit(skb);
}
static inline netdev_tx_t macvlan_netpoll_send_skb(struct macvlan_dev *vlan, struct sk_buff *skb)
{
#ifdef CONFIG_NET_POLL_CONTROLLER
if (vlan->netpoll)
netpoll_send_skb(vlan->netpoll, skb);
#else
BUG();
#endif
return NETDEV_TX_OK;
}
static netdev_tx_t macvlan_start_xmit(struct sk_buff *skb,
struct net_device *dev)
{
unsigned int len = skb->len;
int ret;
struct macvlan_dev *vlan = netdev_priv(dev);
if (unlikely(netpoll_tx_running(dev)))
return macvlan_netpoll_send_skb(vlan, skb);
if (vlan->fwd_priv) {
skb->dev = vlan->lowerdev;
net: core: explicitly select a txq before doing l2 forwarding Currently, the tx queue were selected implicitly in ndo_dfwd_start_xmit(). The will cause several issues: - NETIF_F_LLTX were removed for macvlan, so txq lock were done for macvlan instead of lower device which misses the necessary txq synchronization for lower device such as txq stopping or frozen required by dev watchdog or control path. - dev_hard_start_xmit() was called with NULL txq which bypasses the net device watchdog. - dev_hard_start_xmit() does not check txq everywhere which will lead a crash when tso is disabled for lower device. Fix this by explicitly introducing a new param for .ndo_select_queue() for just selecting queues in the case of l2 forwarding offload. netdev_pick_tx() was also extended to accept this parameter and dev_queue_xmit_accel() was used to do l2 forwarding transmission. With this fixes, NETIF_F_LLTX could be preserved for macvlan and there's no need to check txq against NULL in dev_hard_start_xmit(). Also there's no need to keep a dedicated ndo_dfwd_start_xmit() and we can just reuse the code of dev_queue_xmit() to do the transmission. In the future, it was also required for macvtap l2 forwarding support since it provides a necessary synchronization method. Cc: John Fastabend <john.r.fastabend@intel.com> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: e1000-devel@lists.sourceforge.net Signed-off-by: Jason Wang <jasowang@redhat.com> Acked-by: Neil Horman <nhorman@tuxdriver.com> Acked-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-10 16:18:26 +08:00
ret = dev_queue_xmit_accel(skb, vlan->fwd_priv);
} else {
ret = macvlan_queue_xmit(skb, dev);
}
if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
struct vlan_pcpu_stats *pcpu_stats;
pcpu_stats = this_cpu_ptr(vlan->pcpu_stats);
u64_stats_update_begin(&pcpu_stats->syncp);
pcpu_stats->tx_packets++;
pcpu_stats->tx_bytes += len;
u64_stats_update_end(&pcpu_stats->syncp);
} else {
this_cpu_inc(vlan->pcpu_stats->tx_dropped);
}
return ret;
}
static int macvlan_hard_header(struct sk_buff *skb, struct net_device *dev,
unsigned short type, const void *daddr,
const void *saddr, unsigned len)
{
const struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *lowerdev = vlan->lowerdev;
return dev_hard_header(skb, lowerdev, type, daddr,
saddr ? : dev->dev_addr, len);
}
static const struct header_ops macvlan_hard_header_ops = {
.create = macvlan_hard_header,
.parse = eth_header_parse,
.cache = eth_header_cache,
.cache_update = eth_header_cache_update,
};
static struct rtnl_link_ops macvlan_link_ops;
static int macvlan_open(struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *lowerdev = vlan->lowerdev;
int err;
if (vlan->port->passthru) {
if (!(vlan->flags & MACVLAN_FLAG_NOPROMISC)) {
err = dev_set_promiscuity(lowerdev, 1);
if (err < 0)
goto out;
}
goto hash_add;
}
if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD &&
dev->rtnl_link_ops == &macvlan_link_ops) {
vlan->fwd_priv =
lowerdev->netdev_ops->ndo_dfwd_add_station(lowerdev, dev);
/* If we get a NULL pointer back, or if we get an error
* then we should just fall through to the non accelerated path
*/
if (IS_ERR_OR_NULL(vlan->fwd_priv)) {
vlan->fwd_priv = NULL;
net: core: explicitly select a txq before doing l2 forwarding Currently, the tx queue were selected implicitly in ndo_dfwd_start_xmit(). The will cause several issues: - NETIF_F_LLTX were removed for macvlan, so txq lock were done for macvlan instead of lower device which misses the necessary txq synchronization for lower device such as txq stopping or frozen required by dev watchdog or control path. - dev_hard_start_xmit() was called with NULL txq which bypasses the net device watchdog. - dev_hard_start_xmit() does not check txq everywhere which will lead a crash when tso is disabled for lower device. Fix this by explicitly introducing a new param for .ndo_select_queue() for just selecting queues in the case of l2 forwarding offload. netdev_pick_tx() was also extended to accept this parameter and dev_queue_xmit_accel() was used to do l2 forwarding transmission. With this fixes, NETIF_F_LLTX could be preserved for macvlan and there's no need to check txq against NULL in dev_hard_start_xmit(). Also there's no need to keep a dedicated ndo_dfwd_start_xmit() and we can just reuse the code of dev_queue_xmit() to do the transmission. In the future, it was also required for macvtap l2 forwarding support since it provides a necessary synchronization method. Cc: John Fastabend <john.r.fastabend@intel.com> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: e1000-devel@lists.sourceforge.net Signed-off-by: Jason Wang <jasowang@redhat.com> Acked-by: Neil Horman <nhorman@tuxdriver.com> Acked-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-10 16:18:26 +08:00
} else
return 0;
}
err = -EBUSY;
if (macvlan_addr_busy(vlan->port, dev->dev_addr))
goto out;
err = dev_uc_add(lowerdev, dev->dev_addr);
if (err < 0)
goto out;
if (dev->flags & IFF_ALLMULTI) {
err = dev_set_allmulti(lowerdev, 1);
if (err < 0)
goto del_unicast;
}
if (dev->flags & IFF_PROMISC) {
err = dev_set_promiscuity(lowerdev, 1);
if (err < 0)
goto clear_multi;
}
hash_add:
macvlan_hash_add(vlan);
return 0;
clear_multi:
if (dev->flags & IFF_ALLMULTI)
dev_set_allmulti(lowerdev, -1);
del_unicast:
dev_uc_del(lowerdev, dev->dev_addr);
out:
if (vlan->fwd_priv) {
lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev,
vlan->fwd_priv);
vlan->fwd_priv = NULL;
}
return err;
}
static int macvlan_stop(struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *lowerdev = vlan->lowerdev;
if (vlan->fwd_priv) {
lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev,
vlan->fwd_priv);
vlan->fwd_priv = NULL;
return 0;
}
dev_uc_unsync(lowerdev, dev);
dev_mc_unsync(lowerdev, dev);
if (vlan->port->passthru) {
if (!(vlan->flags & MACVLAN_FLAG_NOPROMISC))
dev_set_promiscuity(lowerdev, -1);
goto hash_del;
}
if (dev->flags & IFF_ALLMULTI)
dev_set_allmulti(lowerdev, -1);
if (dev->flags & IFF_PROMISC)
dev_set_promiscuity(lowerdev, -1);
dev_uc_del(lowerdev, dev->dev_addr);
hash_del:
macvlan_hash_del(vlan, !dev->dismantle);
return 0;
}
static int macvlan_sync_address(struct net_device *dev, unsigned char *addr)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *lowerdev = vlan->lowerdev;
int err;
if (!(dev->flags & IFF_UP)) {
/* Just copy in the new address */
ether_addr_copy(dev->dev_addr, addr);
} else {
/* Rehash and update the device filters */
if (macvlan_addr_busy(vlan->port, addr))
return -EBUSY;
if (!vlan->port->passthru) {
err = dev_uc_add(lowerdev, addr);
if (err)
return err;
dev_uc_del(lowerdev, dev->dev_addr);
}
macvlan_hash_change_addr(vlan, addr);
}
return 0;
}
static int macvlan_set_mac_address(struct net_device *dev, void *p)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct sockaddr *addr = p;
if (!is_valid_ether_addr(addr->sa_data))
return -EADDRNOTAVAIL;
if (vlan->mode == MACVLAN_MODE_PASSTHRU) {
dev_set_mac_address(vlan->lowerdev, addr);
return 0;
}
return macvlan_sync_address(dev, addr->sa_data);
}
static void macvlan_change_rx_flags(struct net_device *dev, int change)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *lowerdev = vlan->lowerdev;
if (dev->flags & IFF_UP) {
if (change & IFF_ALLMULTI)
dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1);
if (change & IFF_PROMISC)
dev_set_promiscuity(lowerdev,
dev->flags & IFF_PROMISC ? 1 : -1);
}
}
static void macvlan_compute_filter(unsigned long *mc_filter,
struct net_device *dev,
struct macvlan_dev *vlan)
{
if (dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) {
bitmap_fill(mc_filter, MACVLAN_MC_FILTER_SZ);
} else {
struct netdev_hw_addr *ha;
DECLARE_BITMAP(filter, MACVLAN_MC_FILTER_SZ);
bitmap_zero(filter, MACVLAN_MC_FILTER_SZ);
netdev_for_each_mc_addr(ha, dev) {
__set_bit(mc_hash(vlan, ha->addr), filter);
}
__set_bit(mc_hash(vlan, dev->broadcast), filter);
bitmap_copy(mc_filter, filter, MACVLAN_MC_FILTER_SZ);
}
}
static void macvlan_set_mac_lists(struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
macvlan_compute_filter(vlan->mc_filter, dev, vlan);
dev_uc_sync(vlan->lowerdev, dev);
dev_mc_sync(vlan->lowerdev, dev);
/* This is slightly inaccurate as we're including the subscription
* list of vlan->lowerdev too.
*
* Bug alert: This only works if everyone has the same broadcast
* address as lowerdev. As soon as someone changes theirs this
* will break.
*
* However, this is already broken as when you change your broadcast
* address we don't get called.
*
* The solution is to maintain a list of broadcast addresses like
* we do for uc/mc, if you care.
*/
macvlan_compute_filter(vlan->port->mc_filter, vlan->lowerdev, NULL);
}
static int macvlan_change_mtu(struct net_device *dev, int new_mtu)
{
struct macvlan_dev *vlan = netdev_priv(dev);
net: use core MTU range checking in core net infra geneve: - Merge __geneve_change_mtu back into geneve_change_mtu, set max_mtu - This one isn't quite as straight-forward as others, could use some closer inspection and testing macvlan: - set min/max_mtu tun: - set min/max_mtu, remove tun_net_change_mtu vxlan: - Merge __vxlan_change_mtu back into vxlan_change_mtu - Set max_mtu to IP_MAX_MTU and retain dynamic MTU range checks in change_mtu function - This one is also not as straight-forward and could use closer inspection and testing from vxlan folks bridge: - set max_mtu of IP_MAX_MTU and retain dynamic MTU range checks in change_mtu function openvswitch: - set min/max_mtu, remove internal_dev_change_mtu - note: max_mtu wasn't checked previously, it's been set to 65535, which is the largest possible size supported sch_teql: - set min/max_mtu (note: max_mtu previously unchecked, used max of 65535) macsec: - min_mtu = 0, max_mtu = 65535 macvlan: - min_mtu = 0, max_mtu = 65535 ntb_netdev: - min_mtu = 0, max_mtu = 65535 veth: - min_mtu = 68, max_mtu = 65535 8021q: - min_mtu = 0, max_mtu = 65535 CC: netdev@vger.kernel.org CC: Nicolas Dichtel <nicolas.dichtel@6wind.com> CC: Hannes Frederic Sowa <hannes@stressinduktion.org> CC: Tom Herbert <tom@herbertland.com> CC: Daniel Borkmann <daniel@iogearbox.net> CC: Alexander Duyck <alexander.h.duyck@intel.com> CC: Paolo Abeni <pabeni@redhat.com> CC: Jiri Benc <jbenc@redhat.com> CC: WANG Cong <xiyou.wangcong@gmail.com> CC: Roopa Prabhu <roopa@cumulusnetworks.com> CC: Pravin B Shelar <pshelar@ovn.org> CC: Sabrina Dubroca <sd@queasysnail.net> CC: Patrick McHardy <kaber@trash.net> CC: Stephen Hemminger <stephen@networkplumber.org> CC: Pravin Shelar <pshelar@nicira.com> CC: Maxim Krasnyansky <maxk@qti.qualcomm.com> Signed-off-by: Jarod Wilson <jarod@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-21 01:55:20 +08:00
if (vlan->lowerdev->mtu < new_mtu)
return -EINVAL;
dev->mtu = new_mtu;
return 0;
}
/*
* macvlan network devices have devices nesting below it and are a special
* "super class" of normal network devices; split their locks off into a
* separate class since they always nest.
*/
static struct lock_class_key macvlan_netdev_addr_lock_key;
macvlan: Add support for 'always_on' offload features Macvlan currently inherits all of its features from the lower device. When lower device disables offload support, this causes macvlan to disable offload support as well. This causes performance regression when using macvlan/macvtap in bridge mode. It can be easily demonstrated by creating 2 namespaces using macvlan in bridge mode and running netperf between them: MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 87380 16384 16384 20.00 1204.61 To restore the performance, we add software offload features to the list of "always_on" features for macvlan. This way when a namespace or a guest using macvtap initially sends a packet, this packet will not be segmented at macvlan level. It will only be segmented when macvlan sends the packet to the lower device. MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 87380 16384 16384 20.00 5507.35 Fixes: 6acf54f1cf0a6747bac9fea26f34cfc5a9029523 (macvtap: Add support of packet capture on macvtap device.) Fixes: 797f87f83b60685ff8a13fa0572d2f10393c50d3 (macvlan: fix netdev feature propagation from lower device) CC: Florian Westphal <fw@strlen.de> CC: Christian Borntraeger <borntraeger@de.ibm.com> CC: Jason Wang <jasowang@redhat.com> CC: Michael S. Tsirkin <mst@redhat.com> Tested-by: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-04 04:33:53 +08:00
#define ALWAYS_ON_FEATURES \
(NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | NETIF_F_LLTX | \
NETIF_F_GSO_ROBUST)
macvlan: Add support for 'always_on' offload features Macvlan currently inherits all of its features from the lower device. When lower device disables offload support, this causes macvlan to disable offload support as well. This causes performance regression when using macvlan/macvtap in bridge mode. It can be easily demonstrated by creating 2 namespaces using macvlan in bridge mode and running netperf between them: MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 87380 16384 16384 20.00 1204.61 To restore the performance, we add software offload features to the list of "always_on" features for macvlan. This way when a namespace or a guest using macvtap initially sends a packet, this packet will not be segmented at macvlan level. It will only be segmented when macvlan sends the packet to the lower device. MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 87380 16384 16384 20.00 5507.35 Fixes: 6acf54f1cf0a6747bac9fea26f34cfc5a9029523 (macvtap: Add support of packet capture on macvtap device.) Fixes: 797f87f83b60685ff8a13fa0572d2f10393c50d3 (macvlan: fix netdev feature propagation from lower device) CC: Florian Westphal <fw@strlen.de> CC: Christian Borntraeger <borntraeger@de.ibm.com> CC: Jason Wang <jasowang@redhat.com> CC: Michael S. Tsirkin <mst@redhat.com> Tested-by: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-04 04:33:53 +08:00
#define MACVLAN_FEATURES \
(NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \
NETIF_F_GSO | NETIF_F_TSO | NETIF_F_UFO | NETIF_F_LRO | \
NETIF_F_TSO_ECN | NETIF_F_TSO6 | NETIF_F_GRO | NETIF_F_RXCSUM | \
NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER)
#define MACVLAN_STATE_MASK \
((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT))
macvlan: Fix lockdep warnings with stacked macvlan devices Macvlan devices try to avoid stacking, but that's not always successfull or even desired. As an example, the following configuration is perefectly legal and valid: eth0 <--- macvlan0 <---- vlan0.10 <--- macvlan1 However, this configuration produces the following lockdep trace: [ 115.620418] ====================================================== [ 115.620477] [ INFO: possible circular locking dependency detected ] [ 115.620516] 3.15.0-rc1+ #24 Not tainted [ 115.620540] ------------------------------------------------------- [ 115.620577] ip/1704 is trying to acquire lock: [ 115.620604] (&vlan_netdev_addr_lock_key/1){+.....}, at: [<ffffffff815df49c>] dev_uc_sync+0x3c/0x80 [ 115.620686] but task is already holding lock: [ 115.620723] (&macvlan_netdev_addr_lock_key){+.....}, at: [<ffffffff815da5be>] dev_set_rx_mode+0x1e/0x40 [ 115.620795] which lock already depends on the new lock. [ 115.620853] the existing dependency chain (in reverse order) is: [ 115.620894] -> #1 (&macvlan_netdev_addr_lock_key){+.....}: [ 115.620935] [<ffffffff810d57f2>] lock_acquire+0xa2/0x130 [ 115.620974] [<ffffffff816f62e7>] _raw_spin_lock_nested+0x37/0x50 [ 115.621019] [<ffffffffa07296c3>] vlan_dev_set_rx_mode+0x53/0x110 [8021q] [ 115.621066] [<ffffffff815da557>] __dev_set_rx_mode+0x57/0xa0 [ 115.621105] [<ffffffff815da5c6>] dev_set_rx_mode+0x26/0x40 [ 115.621143] [<ffffffff815da6be>] __dev_open+0xde/0x140 [ 115.621174] [<ffffffff815da9ad>] __dev_change_flags+0x9d/0x170 [ 115.621174] [<ffffffff815daaa9>] dev_change_flags+0x29/0x60 [ 115.621174] [<ffffffff815e7f11>] do_setlink+0x321/0x9a0 [ 115.621174] [<ffffffff815ea59f>] rtnl_newlink+0x51f/0x730 [ 115.621174] [<ffffffff815e6e75>] rtnetlink_rcv_msg+0x95/0x250 [ 115.621174] [<ffffffff81608b19>] netlink_rcv_skb+0xa9/0xc0 [ 115.621174] [<ffffffff815e6dca>] rtnetlink_rcv+0x2a/0x40 [ 115.621174] [<ffffffff81608150>] netlink_unicast+0xf0/0x1c0 [ 115.621174] [<ffffffff8160851f>] netlink_sendmsg+0x2ff/0x740 [ 115.621174] [<ffffffff815bc9db>] sock_sendmsg+0x8b/0xc0 [ 115.621174] [<ffffffff815bd4b9>] ___sys_sendmsg+0x369/0x380 [ 115.621174] [<ffffffff815bdbb2>] __sys_sendmsg+0x42/0x80 [ 115.621174] [<ffffffff815bdc02>] SyS_sendmsg+0x12/0x20 [ 115.621174] [<ffffffff816ffd69>] system_call_fastpath+0x16/0x1b [ 115.621174] -> #0 (&vlan_netdev_addr_lock_key/1){+.....}: [ 115.621174] [<ffffffff810d4d43>] __lock_acquire+0x1773/0x1a60 [ 115.621174] [<ffffffff810d57f2>] lock_acquire+0xa2/0x130 [ 115.621174] [<ffffffff816f62e7>] _raw_spin_lock_nested+0x37/0x50 [ 115.621174] [<ffffffff815df49c>] dev_uc_sync+0x3c/0x80 [ 115.621174] [<ffffffffa0696d2a>] macvlan_set_mac_lists+0xca/0x110 [macvlan] [ 115.621174] [<ffffffff815da557>] __dev_set_rx_mode+0x57/0xa0 [ 115.621174] [<ffffffff815da5c6>] dev_set_rx_mode+0x26/0x40 [ 115.621174] [<ffffffff815da6be>] __dev_open+0xde/0x140 [ 115.621174] [<ffffffff815da9ad>] __dev_change_flags+0x9d/0x170 [ 115.621174] [<ffffffff815daaa9>] dev_change_flags+0x29/0x60 [ 115.621174] [<ffffffff815e7f11>] do_setlink+0x321/0x9a0 [ 115.621174] [<ffffffff815ea59f>] rtnl_newlink+0x51f/0x730 [ 115.621174] [<ffffffff815e6e75>] rtnetlink_rcv_msg+0x95/0x250 [ 115.621174] [<ffffffff81608b19>] netlink_rcv_skb+0xa9/0xc0 [ 115.621174] [<ffffffff815e6dca>] rtnetlink_rcv+0x2a/0x40 [ 115.621174] [<ffffffff81608150>] netlink_unicast+0xf0/0x1c0 [ 115.621174] [<ffffffff8160851f>] netlink_sendmsg+0x2ff/0x740 [ 115.621174] [<ffffffff815bc9db>] sock_sendmsg+0x8b/0xc0 [ 115.621174] [<ffffffff815bd4b9>] ___sys_sendmsg+0x369/0x380 [ 115.621174] [<ffffffff815bdbb2>] __sys_sendmsg+0x42/0x80 [ 115.621174] [<ffffffff815bdc02>] SyS_sendmsg+0x12/0x20 [ 115.621174] [<ffffffff816ffd69>] system_call_fastpath+0x16/0x1b [ 115.621174] other info that might help us debug this: [ 115.621174] Possible unsafe locking scenario: [ 115.621174] CPU0 CPU1 [ 115.621174] ---- ---- [ 115.621174] lock(&macvlan_netdev_addr_lock_key); [ 115.621174] lock(&vlan_netdev_addr_lock_key/1); [ 115.621174] lock(&macvlan_netdev_addr_lock_key); [ 115.621174] lock(&vlan_netdev_addr_lock_key/1); [ 115.621174] *** DEADLOCK *** [ 115.621174] 2 locks held by ip/1704: [ 115.621174] #0: (rtnl_mutex){+.+.+.}, at: [<ffffffff815e6dbb>] rtnetlink_rcv+0x1b/0x40 [ 115.621174] #1: (&macvlan_netdev_addr_lock_key){+.....}, at: [<ffffffff815da5be>] dev_set_rx_mode+0x1e/0x40 [ 115.621174] stack backtrace: [ 115.621174] CPU: 3 PID: 1704 Comm: ip Not tainted 3.15.0-rc1+ #24 [ 115.621174] Hardware name: Hewlett-Packard HP xw8400 Workstation/0A08h, BIOS 786D5 v02.38 10/25/2010 [ 115.621174] ffffffff82339ae0 ffff880465f79568 ffffffff816ee20c ffffffff82339ae0 [ 115.621174] ffff880465f795a8 ffffffff816e9e1b ffff880465f79600 ffff880465b019c8 [ 115.621174] 0000000000000001 0000000000000002 ffff880465b019c8 ffff880465b01230 [ 115.621174] Call Trace: [ 115.621174] [<ffffffff816ee20c>] dump_stack+0x4d/0x66 [ 115.621174] [<ffffffff816e9e1b>] print_circular_bug+0x200/0x20e [ 115.621174] [<ffffffff810d4d43>] __lock_acquire+0x1773/0x1a60 [ 115.621174] [<ffffffff810d3172>] ? trace_hardirqs_on_caller+0xb2/0x1d0 [ 115.621174] [<ffffffff810d57f2>] lock_acquire+0xa2/0x130 [ 115.621174] [<ffffffff815df49c>] ? dev_uc_sync+0x3c/0x80 [ 115.621174] [<ffffffff816f62e7>] _raw_spin_lock_nested+0x37/0x50 [ 115.621174] [<ffffffff815df49c>] ? dev_uc_sync+0x3c/0x80 [ 115.621174] [<ffffffff815df49c>] dev_uc_sync+0x3c/0x80 [ 115.621174] [<ffffffffa0696d2a>] macvlan_set_mac_lists+0xca/0x110 [macvlan] [ 115.621174] [<ffffffff815da557>] __dev_set_rx_mode+0x57/0xa0 [ 115.621174] [<ffffffff815da5c6>] dev_set_rx_mode+0x26/0x40 [ 115.621174] [<ffffffff815da6be>] __dev_open+0xde/0x140 [ 115.621174] [<ffffffff815da9ad>] __dev_change_flags+0x9d/0x170 [ 115.621174] [<ffffffff815daaa9>] dev_change_flags+0x29/0x60 [ 115.621174] [<ffffffff811e1db1>] ? mem_cgroup_bad_page_check+0x21/0x30 [ 115.621174] [<ffffffff815e7f11>] do_setlink+0x321/0x9a0 [ 115.621174] [<ffffffff810d394c>] ? __lock_acquire+0x37c/0x1a60 [ 115.621174] [<ffffffff815ea59f>] rtnl_newlink+0x51f/0x730 [ 115.621174] [<ffffffff815ea169>] ? rtnl_newlink+0xe9/0x730 [ 115.621174] [<ffffffff815e6e75>] rtnetlink_rcv_msg+0x95/0x250 [ 115.621174] [<ffffffff810d329d>] ? trace_hardirqs_on+0xd/0x10 [ 115.621174] [<ffffffff815e6dbb>] ? rtnetlink_rcv+0x1b/0x40 [ 115.621174] [<ffffffff815e6de0>] ? rtnetlink_rcv+0x40/0x40 [ 115.621174] [<ffffffff81608b19>] netlink_rcv_skb+0xa9/0xc0 [ 115.621174] [<ffffffff815e6dca>] rtnetlink_rcv+0x2a/0x40 [ 115.621174] [<ffffffff81608150>] netlink_unicast+0xf0/0x1c0 [ 115.621174] [<ffffffff8160851f>] netlink_sendmsg+0x2ff/0x740 [ 115.621174] [<ffffffff815bc9db>] sock_sendmsg+0x8b/0xc0 [ 115.621174] [<ffffffff8119d4af>] ? might_fault+0x5f/0xb0 [ 115.621174] [<ffffffff8119d4f8>] ? might_fault+0xa8/0xb0 [ 115.621174] [<ffffffff8119d4af>] ? might_fault+0x5f/0xb0 [ 115.621174] [<ffffffff815cb51e>] ? verify_iovec+0x5e/0xe0 [ 115.621174] [<ffffffff815bd4b9>] ___sys_sendmsg+0x369/0x380 [ 115.621174] [<ffffffff816faa0d>] ? __do_page_fault+0x11d/0x570 [ 115.621174] [<ffffffff810cfe9f>] ? up_read+0x1f/0x40 [ 115.621174] [<ffffffff816fab04>] ? __do_page_fault+0x214/0x570 [ 115.621174] [<ffffffff8120a10b>] ? mntput_no_expire+0x6b/0x1c0 [ 115.621174] [<ffffffff8120a0b7>] ? mntput_no_expire+0x17/0x1c0 [ 115.621174] [<ffffffff8120a284>] ? mntput+0x24/0x40 [ 115.621174] [<ffffffff815bdbb2>] __sys_sendmsg+0x42/0x80 [ 115.621174] [<ffffffff815bdc02>] SyS_sendmsg+0x12/0x20 [ 115.621174] [<ffffffff816ffd69>] system_call_fastpath+0x16/0x1b Fix this by correctly providing macvlan lockdep class. Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-17 05:04:56 +08:00
static int macvlan_get_nest_level(struct net_device *dev)
{
return ((struct macvlan_dev *)netdev_priv(dev))->nest_level;
}
static void macvlan_set_lockdep_class(struct net_device *dev)
{
netdev_lockdep_set_classes(dev);
macvlan: Fix lockdep warnings with stacked macvlan devices Macvlan devices try to avoid stacking, but that's not always successfull or even desired. As an example, the following configuration is perefectly legal and valid: eth0 <--- macvlan0 <---- vlan0.10 <--- macvlan1 However, this configuration produces the following lockdep trace: [ 115.620418] ====================================================== [ 115.620477] [ INFO: possible circular locking dependency detected ] [ 115.620516] 3.15.0-rc1+ #24 Not tainted [ 115.620540] ------------------------------------------------------- [ 115.620577] ip/1704 is trying to acquire lock: [ 115.620604] (&vlan_netdev_addr_lock_key/1){+.....}, at: [<ffffffff815df49c>] dev_uc_sync+0x3c/0x80 [ 115.620686] but task is already holding lock: [ 115.620723] (&macvlan_netdev_addr_lock_key){+.....}, at: [<ffffffff815da5be>] dev_set_rx_mode+0x1e/0x40 [ 115.620795] which lock already depends on the new lock. [ 115.620853] the existing dependency chain (in reverse order) is: [ 115.620894] -> #1 (&macvlan_netdev_addr_lock_key){+.....}: [ 115.620935] [<ffffffff810d57f2>] lock_acquire+0xa2/0x130 [ 115.620974] [<ffffffff816f62e7>] _raw_spin_lock_nested+0x37/0x50 [ 115.621019] [<ffffffffa07296c3>] vlan_dev_set_rx_mode+0x53/0x110 [8021q] [ 115.621066] [<ffffffff815da557>] __dev_set_rx_mode+0x57/0xa0 [ 115.621105] [<ffffffff815da5c6>] dev_set_rx_mode+0x26/0x40 [ 115.621143] [<ffffffff815da6be>] __dev_open+0xde/0x140 [ 115.621174] [<ffffffff815da9ad>] __dev_change_flags+0x9d/0x170 [ 115.621174] [<ffffffff815daaa9>] dev_change_flags+0x29/0x60 [ 115.621174] [<ffffffff815e7f11>] do_setlink+0x321/0x9a0 [ 115.621174] [<ffffffff815ea59f>] rtnl_newlink+0x51f/0x730 [ 115.621174] [<ffffffff815e6e75>] rtnetlink_rcv_msg+0x95/0x250 [ 115.621174] [<ffffffff81608b19>] netlink_rcv_skb+0xa9/0xc0 [ 115.621174] [<ffffffff815e6dca>] rtnetlink_rcv+0x2a/0x40 [ 115.621174] [<ffffffff81608150>] netlink_unicast+0xf0/0x1c0 [ 115.621174] [<ffffffff8160851f>] netlink_sendmsg+0x2ff/0x740 [ 115.621174] [<ffffffff815bc9db>] sock_sendmsg+0x8b/0xc0 [ 115.621174] [<ffffffff815bd4b9>] ___sys_sendmsg+0x369/0x380 [ 115.621174] [<ffffffff815bdbb2>] __sys_sendmsg+0x42/0x80 [ 115.621174] [<ffffffff815bdc02>] SyS_sendmsg+0x12/0x20 [ 115.621174] [<ffffffff816ffd69>] system_call_fastpath+0x16/0x1b [ 115.621174] -> #0 (&vlan_netdev_addr_lock_key/1){+.....}: [ 115.621174] [<ffffffff810d4d43>] __lock_acquire+0x1773/0x1a60 [ 115.621174] [<ffffffff810d57f2>] lock_acquire+0xa2/0x130 [ 115.621174] [<ffffffff816f62e7>] _raw_spin_lock_nested+0x37/0x50 [ 115.621174] [<ffffffff815df49c>] dev_uc_sync+0x3c/0x80 [ 115.621174] [<ffffffffa0696d2a>] macvlan_set_mac_lists+0xca/0x110 [macvlan] [ 115.621174] [<ffffffff815da557>] __dev_set_rx_mode+0x57/0xa0 [ 115.621174] [<ffffffff815da5c6>] dev_set_rx_mode+0x26/0x40 [ 115.621174] [<ffffffff815da6be>] __dev_open+0xde/0x140 [ 115.621174] [<ffffffff815da9ad>] __dev_change_flags+0x9d/0x170 [ 115.621174] [<ffffffff815daaa9>] dev_change_flags+0x29/0x60 [ 115.621174] [<ffffffff815e7f11>] do_setlink+0x321/0x9a0 [ 115.621174] [<ffffffff815ea59f>] rtnl_newlink+0x51f/0x730 [ 115.621174] [<ffffffff815e6e75>] rtnetlink_rcv_msg+0x95/0x250 [ 115.621174] [<ffffffff81608b19>] netlink_rcv_skb+0xa9/0xc0 [ 115.621174] [<ffffffff815e6dca>] rtnetlink_rcv+0x2a/0x40 [ 115.621174] [<ffffffff81608150>] netlink_unicast+0xf0/0x1c0 [ 115.621174] [<ffffffff8160851f>] netlink_sendmsg+0x2ff/0x740 [ 115.621174] [<ffffffff815bc9db>] sock_sendmsg+0x8b/0xc0 [ 115.621174] [<ffffffff815bd4b9>] ___sys_sendmsg+0x369/0x380 [ 115.621174] [<ffffffff815bdbb2>] __sys_sendmsg+0x42/0x80 [ 115.621174] [<ffffffff815bdc02>] SyS_sendmsg+0x12/0x20 [ 115.621174] [<ffffffff816ffd69>] system_call_fastpath+0x16/0x1b [ 115.621174] other info that might help us debug this: [ 115.621174] Possible unsafe locking scenario: [ 115.621174] CPU0 CPU1 [ 115.621174] ---- ---- [ 115.621174] lock(&macvlan_netdev_addr_lock_key); [ 115.621174] lock(&vlan_netdev_addr_lock_key/1); [ 115.621174] lock(&macvlan_netdev_addr_lock_key); [ 115.621174] lock(&vlan_netdev_addr_lock_key/1); [ 115.621174] *** DEADLOCK *** [ 115.621174] 2 locks held by ip/1704: [ 115.621174] #0: (rtnl_mutex){+.+.+.}, at: [<ffffffff815e6dbb>] rtnetlink_rcv+0x1b/0x40 [ 115.621174] #1: (&macvlan_netdev_addr_lock_key){+.....}, at: [<ffffffff815da5be>] dev_set_rx_mode+0x1e/0x40 [ 115.621174] stack backtrace: [ 115.621174] CPU: 3 PID: 1704 Comm: ip Not tainted 3.15.0-rc1+ #24 [ 115.621174] Hardware name: Hewlett-Packard HP xw8400 Workstation/0A08h, BIOS 786D5 v02.38 10/25/2010 [ 115.621174] ffffffff82339ae0 ffff880465f79568 ffffffff816ee20c ffffffff82339ae0 [ 115.621174] ffff880465f795a8 ffffffff816e9e1b ffff880465f79600 ffff880465b019c8 [ 115.621174] 0000000000000001 0000000000000002 ffff880465b019c8 ffff880465b01230 [ 115.621174] Call Trace: [ 115.621174] [<ffffffff816ee20c>] dump_stack+0x4d/0x66 [ 115.621174] [<ffffffff816e9e1b>] print_circular_bug+0x200/0x20e [ 115.621174] [<ffffffff810d4d43>] __lock_acquire+0x1773/0x1a60 [ 115.621174] [<ffffffff810d3172>] ? trace_hardirqs_on_caller+0xb2/0x1d0 [ 115.621174] [<ffffffff810d57f2>] lock_acquire+0xa2/0x130 [ 115.621174] [<ffffffff815df49c>] ? dev_uc_sync+0x3c/0x80 [ 115.621174] [<ffffffff816f62e7>] _raw_spin_lock_nested+0x37/0x50 [ 115.621174] [<ffffffff815df49c>] ? dev_uc_sync+0x3c/0x80 [ 115.621174] [<ffffffff815df49c>] dev_uc_sync+0x3c/0x80 [ 115.621174] [<ffffffffa0696d2a>] macvlan_set_mac_lists+0xca/0x110 [macvlan] [ 115.621174] [<ffffffff815da557>] __dev_set_rx_mode+0x57/0xa0 [ 115.621174] [<ffffffff815da5c6>] dev_set_rx_mode+0x26/0x40 [ 115.621174] [<ffffffff815da6be>] __dev_open+0xde/0x140 [ 115.621174] [<ffffffff815da9ad>] __dev_change_flags+0x9d/0x170 [ 115.621174] [<ffffffff815daaa9>] dev_change_flags+0x29/0x60 [ 115.621174] [<ffffffff811e1db1>] ? mem_cgroup_bad_page_check+0x21/0x30 [ 115.621174] [<ffffffff815e7f11>] do_setlink+0x321/0x9a0 [ 115.621174] [<ffffffff810d394c>] ? __lock_acquire+0x37c/0x1a60 [ 115.621174] [<ffffffff815ea59f>] rtnl_newlink+0x51f/0x730 [ 115.621174] [<ffffffff815ea169>] ? rtnl_newlink+0xe9/0x730 [ 115.621174] [<ffffffff815e6e75>] rtnetlink_rcv_msg+0x95/0x250 [ 115.621174] [<ffffffff810d329d>] ? trace_hardirqs_on+0xd/0x10 [ 115.621174] [<ffffffff815e6dbb>] ? rtnetlink_rcv+0x1b/0x40 [ 115.621174] [<ffffffff815e6de0>] ? rtnetlink_rcv+0x40/0x40 [ 115.621174] [<ffffffff81608b19>] netlink_rcv_skb+0xa9/0xc0 [ 115.621174] [<ffffffff815e6dca>] rtnetlink_rcv+0x2a/0x40 [ 115.621174] [<ffffffff81608150>] netlink_unicast+0xf0/0x1c0 [ 115.621174] [<ffffffff8160851f>] netlink_sendmsg+0x2ff/0x740 [ 115.621174] [<ffffffff815bc9db>] sock_sendmsg+0x8b/0xc0 [ 115.621174] [<ffffffff8119d4af>] ? might_fault+0x5f/0xb0 [ 115.621174] [<ffffffff8119d4f8>] ? might_fault+0xa8/0xb0 [ 115.621174] [<ffffffff8119d4af>] ? might_fault+0x5f/0xb0 [ 115.621174] [<ffffffff815cb51e>] ? verify_iovec+0x5e/0xe0 [ 115.621174] [<ffffffff815bd4b9>] ___sys_sendmsg+0x369/0x380 [ 115.621174] [<ffffffff816faa0d>] ? __do_page_fault+0x11d/0x570 [ 115.621174] [<ffffffff810cfe9f>] ? up_read+0x1f/0x40 [ 115.621174] [<ffffffff816fab04>] ? __do_page_fault+0x214/0x570 [ 115.621174] [<ffffffff8120a10b>] ? mntput_no_expire+0x6b/0x1c0 [ 115.621174] [<ffffffff8120a0b7>] ? mntput_no_expire+0x17/0x1c0 [ 115.621174] [<ffffffff8120a284>] ? mntput+0x24/0x40 [ 115.621174] [<ffffffff815bdbb2>] __sys_sendmsg+0x42/0x80 [ 115.621174] [<ffffffff815bdc02>] SyS_sendmsg+0x12/0x20 [ 115.621174] [<ffffffff816ffd69>] system_call_fastpath+0x16/0x1b Fix this by correctly providing macvlan lockdep class. Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-17 05:04:56 +08:00
lockdep_set_class_and_subclass(&dev->addr_list_lock,
&macvlan_netdev_addr_lock_key,
macvlan_get_nest_level(dev));
}
static int macvlan_init(struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
const struct net_device *lowerdev = vlan->lowerdev;
struct macvlan_port *port = vlan->port;
dev->state = (dev->state & ~MACVLAN_STATE_MASK) |
(lowerdev->state & MACVLAN_STATE_MASK);
dev->features = lowerdev->features & MACVLAN_FEATURES;
macvlan: Add support for 'always_on' offload features Macvlan currently inherits all of its features from the lower device. When lower device disables offload support, this causes macvlan to disable offload support as well. This causes performance regression when using macvlan/macvtap in bridge mode. It can be easily demonstrated by creating 2 namespaces using macvlan in bridge mode and running netperf between them: MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 87380 16384 16384 20.00 1204.61 To restore the performance, we add software offload features to the list of "always_on" features for macvlan. This way when a namespace or a guest using macvtap initially sends a packet, this packet will not be segmented at macvlan level. It will only be segmented when macvlan sends the packet to the lower device. MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 87380 16384 16384 20.00 5507.35 Fixes: 6acf54f1cf0a6747bac9fea26f34cfc5a9029523 (macvtap: Add support of packet capture on macvtap device.) Fixes: 797f87f83b60685ff8a13fa0572d2f10393c50d3 (macvlan: fix netdev feature propagation from lower device) CC: Florian Westphal <fw@strlen.de> CC: Christian Borntraeger <borntraeger@de.ibm.com> CC: Jason Wang <jasowang@redhat.com> CC: Michael S. Tsirkin <mst@redhat.com> Tested-by: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-04 04:33:53 +08:00
dev->features |= ALWAYS_ON_FEATURES;
dev->hw_features |= NETIF_F_LRO;
dev->vlan_features = lowerdev->vlan_features & MACVLAN_FEATURES;
dev->gso_max_size = lowerdev->gso_max_size;
dev->gso_max_segs = lowerdev->gso_max_segs;
drivers/net/macvlan.c: fix cloning of tagged VLAN interfaces Addresses http://bugzilla.kernel.org/show_bug.cgi?id=13348 akpm: the reporter disappeared, so I typed it in again. It is not possible to make clone of tagged VLAN interface to be used as mac-based vlan interfave. How reproducible: Use any 802.1q tagged vlan interface, e.g. eth2.700 and clone it: ip link add link eth2.700 address 00:04:75:cb:38:09 macvlan0 type macvlan ip link set dev macvlan0 up ip addr add 10.195.1.1/24 dev macvlan0 So far, so good. Now try to ping anything via macvlan0: ping 10.195.1.2 Actual results: For every attempted packet tx kernel writes to console: ------------[ cut here ]------------ WARNING: at net/8021q/vlan_dev.c:254 vlan_dev_hard_header+0x36/0x126 [8021q]() Hardware name: M22ES Modules linked in: arptable_filter arp_tables bridge veth macvlan arc4 ecb ppp_mppe ppp_async crc_ccitt ppp_generic slhc autofs4 sunrpc 8021q garp stp ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 xt_state nf_conntrack xt_tcpudp x_tables dm_mirror dm_region_hash dm_log dm_multipath dm_mod sbs sbshc lp floppy snd_intel8x0 joydev snd_seq_dummy snd_intel8x0m snd_ac97_codec ide_cd_mod ac97_bus snd_seq_oss cdrom snd_seq_midi_event serio_raw snd_seq snd_seq_device snd_pcm_oss snd_mixer_oss parport_pc snd_pcm parport battery 8139cp snd_timer i2c_sis96x ac button snd rtc_cmos rtc_core 8139too soundcore rtc_lib mii i2c_core pcspkr snd_page_alloc pata_sis libata sd_mod scsi_mod ext3 jbd ehci_hcd ohci_hcd uhci_hcd [last unloaded: ip_tables] Pid: 0, comm: swapper Tainted: G W 2.6.29.3 #1 Call Trace: [<c0425f48>] warn_slowpath+0x60/0x9f [<c0425f6f>] warn_slowpath+0x87/0x9f [<dffb850d>] vlan_dev_hard_header+0x0/0x126 [8021q] [<dffb8543>] vlan_dev_hard_header+0x36/0x126 [8021q] [<dffb850d>] vlan_dev_hard_header+0x0/0x126 [8021q] [<df83155d>] macvlan_hard_header+0x3c/0x47 [macvlan] [<df831521>] macvlan_hard_header+0x0/0x47 [macvlan] [<c062bf3f>] arp_create+0xef/0x1ff [<c062c08c>] arp_send+0x3d/0x54 [<c062c916>] arp_solicit+0x16c/0x177 [<c05fadd2>] neigh_timer_handler+0x227/0x269 [<c05fabab>] neigh_timer_handler+0x0/0x269 [<c042ce4d>] run_timer_softirq+0xf0/0x141 [<c0429e5a>] __do_softirq+0x76/0xf8 [<c0429de4>] __do_softirq+0x0/0xf8 <IRQ> [<c044fb67>] handle_level_irq+0x0/0xad [<c0429db7>] irq_exit+0x35/0x62 [<c04046bb>] do_IRQ+0xdf/0xf4 [<c04035a7>] common_interrupt+0x27/0x2c [<c04079c5>] default_idle+0x2a/0x3d [<c0401bb6>] cpu_idle+0x57/0x70 Macvlan driver always uses standard ethernet header length for all types of interface to which it is linked. This patch fixes this problem. Reported-by: <sg.tweak@gmail.com> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: "David S. Miller" <davem@davemloft.net> Cc: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-10 17:55:02 +08:00
dev->hard_header_len = lowerdev->hard_header_len;
macvlan_set_lockdep_class(dev);
vlan->pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats);
if (!vlan->pcpu_stats)
return -ENOMEM;
port->count += 1;
return 0;
}
static void macvlan_uninit(struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct macvlan_port *port = vlan->port;
free_percpu(vlan->pcpu_stats);
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
macvlan_flush_sources(port, vlan);
Revert "macvlan: simplify the structure port" This reverts commit a188a54d11629bef2169052297e61f3767ca8ce5. It causes crashes ==================== [ 80.643286] BUG: unable to handle kernel NULL pointer dereference at 0000000000000878 [ 80.670103] IP: [<ffffffff810832e4>] try_to_grab_pending+0x64/0x1f0 [ 80.691289] PGD 22c102067 PUD 235bf0067 PMD 0 [ 80.706611] Oops: 0002 [#1] SMP [ 80.717836] Modules linked in: macvlan nfsd lockd nfs_acl exportfs auth_rpcgss sunrpc oid_registry ioatdma ixgbe(-) mdio igb dca [ 80.757935] CPU: 37 PID: 6724 Comm: rmmod Not tainted 3.16.0-net-next-08-12-2014-FCoE+ #1 [ 80.785688] Hardware name: Intel Corporation S2600CO/S2600CO, BIOS SE5C600.86B.02.03.0003.041920141333 04/19/2014 [ 80.820310] task: ffff880235a9eae0 ti: ffff88022e844000 task.ti: ffff88022e844000 [ 80.845770] RIP: 0010:[<ffffffff810832e4>] [<ffffffff810832e4>] try_to_grab_pending+0x64/0x1f0 [ 80.875326] RSP: 0018:ffff88022e847b28 EFLAGS: 00010046 [ 80.893251] RAX: 0000000000037a6a RBX: 0000000000000878 RCX: 0000000000000000 [ 80.917187] RDX: ffff880235a9eae0 RSI: 0000000000000001 RDI: ffffffff810832db [ 80.941125] RBP: ffff88022e847b58 R08: 0000000000000000 R09: 0000000000000000 [ 80.965056] R10: 0000000000000001 R11: 0000000000000001 R12: ffff88022e847b70 [ 80.988994] R13: 0000000000000000 R14: ffff88022e847be8 R15: ffffffff81ebe440 [ 81.012929] FS: 00007fab90b07700(0000) GS:ffff88043f7a0000(0000) knlGS:0000000000000000 [ 81.040400] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 81.059757] CR2: 0000000000000878 CR3: 0000000235a42000 CR4: 00000000001407e0 [ 81.083689] Stack: [ 81.090739] ffff880235a9eae0 0000000000000878 ffff88022e847b70 0000000000000000 [ 81.116253] ffff88022e847be8 ffffffff81ebe440 ffff88022e847b98 ffffffff810847f1 [ 81.141766] ffff88022e847b78 0000000000000286 ffff880234200000 0000000000000000 [ 81.167282] Call Trace: [ 81.175768] [<ffffffff810847f1>] __cancel_work_timer+0x31/0x170 [ 81.195985] [<ffffffff8108494b>] cancel_work_sync+0xb/0x10 [ 81.214769] [<ffffffffa015ae68>] macvlan_port_destroy+0x28/0x60 [macvlan] [ 81.237844] [<ffffffffa015b930>] macvlan_uninit+0x40/0x50 [macvlan] [ 81.259209] [<ffffffff816bf6e2>] rollback_registered_many+0x1a2/0x2c0 [ 81.281140] [<ffffffff816bf81a>] unregister_netdevice_many+0x1a/0xb0 [ 81.302786] [<ffffffffa015a4ff>] macvlan_device_event+0x1ef/0x240 [macvlan] [ 81.326439] [<ffffffff8108a13d>] notifier_call_chain+0x4d/0x70 [ 81.346366] [<ffffffff8108a201>] raw_notifier_call_chain+0x11/0x20 [ 81.367439] [<ffffffff816bf25b>] call_netdevice_notifiers_info+0x3b/0x70 [ 81.390228] [<ffffffff816bf2a1>] call_netdevice_notifiers+0x11/0x20 [ 81.411587] [<ffffffff816bf6bd>] rollback_registered_many+0x17d/0x2c0 [ 81.433518] [<ffffffff816bf925>] unregister_netdevice_queue+0x75/0x110 [ 81.455735] [<ffffffff816bfb2b>] unregister_netdev+0x1b/0x30 [ 81.475094] [<ffffffffa0039b50>] ixgbe_remove+0x170/0x1d0 [ixgbe] [ 81.495886] [<ffffffff813512a2>] pci_device_remove+0x32/0x60 [ 81.515246] [<ffffffff814c75c4>] __device_release_driver+0x64/0xd0 [ 81.536321] [<ffffffff814c76f8>] driver_detach+0xc8/0xd0 [ 81.554530] [<ffffffff814c656e>] bus_remove_driver+0x4e/0xa0 [ 81.573888] [<ffffffff814c828b>] driver_unregister+0x2b/0x60 [ 81.593246] [<ffffffff8135143e>] pci_unregister_driver+0x1e/0xa0 [ 81.613749] [<ffffffffa005db18>] ixgbe_exit_module+0x1c/0x2e [ixgbe] [ 81.635401] [<ffffffff810e738b>] SyS_delete_module+0x15b/0x1e0 [ 81.655334] [<ffffffff8187a395>] ? sysret_check+0x22/0x5d [ 81.673833] [<ffffffff810abd2d>] ? trace_hardirqs_on_caller+0x11d/0x1e0 [ 81.696339] [<ffffffff8132bfde>] ? trace_hardirqs_on_thunk+0x3a/0x3f [ 81.717985] [<ffffffff8187a369>] system_call_fastpath+0x16/0x1b [ 81.738199] Code: 00 48 83 3d 6e bb da 00 00 48 89 c2 0f 84 67 01 00 00 fa 66 0f 1f 44 00 00 49 89 14 24 e8 b5 4b 02 00 45 84 ed 0f 85 ac 00 00 00 <f0> 0f ba 2b 00 72 1d 31 c0 48 8b 5d d8 4c 8b 65 e0 4c 8b 6d e8 [ 81.807026] RIP [<ffffffff810832e4>] try_to_grab_pending+0x64/0x1f0 [ 81.828468] RSP <ffff88022e847b28> [ 81.840384] CR2: 0000000000000878 [ 81.851731] ---[ end trace 9f6c7232e3464e11 ]--- ==================== This bug could be triggered by these steps: modprobe ixgbe ; modprobe macvlan ip link add link p96p1 address 00:1B:21:6E:06:00 macvlan0 type macvlan ip link add link p96p1 address 00:1B:21:6E:06:01 macvlan1 type macvlan ip link add link p96p1 address 00:1B:21:6E:06:02 macvlan2 type macvlan ip link add link p96p1 address 00:1B:21:6E:06:03 macvlan3 type macvlan rmmod ixgbe Reported-by: "Keller, Jacob E" <jacob.e.keller@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-08-15 05:32:49 +08:00
port->count -= 1;
if (!port->count)
macvlan_port_destroy(port->dev);
}
static void macvlan_dev_get_stats64(struct net_device *dev,
struct rtnl_link_stats64 *stats)
{
struct macvlan_dev *vlan = netdev_priv(dev);
if (vlan->pcpu_stats) {
struct vlan_pcpu_stats *p;
u64 rx_packets, rx_bytes, rx_multicast, tx_packets, tx_bytes;
u32 rx_errors = 0, tx_dropped = 0;
unsigned int start;
int i;
for_each_possible_cpu(i) {
p = per_cpu_ptr(vlan->pcpu_stats, i);
do {
start = u64_stats_fetch_begin_irq(&p->syncp);
rx_packets = p->rx_packets;
rx_bytes = p->rx_bytes;
rx_multicast = p->rx_multicast;
tx_packets = p->tx_packets;
tx_bytes = p->tx_bytes;
} while (u64_stats_fetch_retry_irq(&p->syncp, start));
stats->rx_packets += rx_packets;
stats->rx_bytes += rx_bytes;
stats->multicast += rx_multicast;
stats->tx_packets += tx_packets;
stats->tx_bytes += tx_bytes;
/* rx_errors & tx_dropped are u32, updated
* without syncp protection.
*/
rx_errors += p->rx_errors;
tx_dropped += p->tx_dropped;
}
stats->rx_errors = rx_errors;
stats->rx_dropped = rx_errors;
stats->tx_dropped = tx_dropped;
}
}
static int macvlan_vlan_rx_add_vid(struct net_device *dev,
__be16 proto, u16 vid)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *lowerdev = vlan->lowerdev;
return vlan_vid_add(lowerdev, proto, vid);
}
static int macvlan_vlan_rx_kill_vid(struct net_device *dev,
__be16 proto, u16 vid)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *lowerdev = vlan->lowerdev;
vlan_vid_del(lowerdev, proto, vid);
return 0;
}
static int macvlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr, u16 vid,
u16 flags)
{
struct macvlan_dev *vlan = netdev_priv(dev);
int err = -EINVAL;
/* Support unicast filter only on passthru devices.
* Multicast filter should be allowed on all devices.
*/
if (!vlan->port->passthru && is_unicast_ether_addr(addr))
return -EOPNOTSUPP;
if (flags & NLM_F_REPLACE)
return -EOPNOTSUPP;
if (is_unicast_ether_addr(addr))
err = dev_uc_add_excl(dev, addr);
else if (is_multicast_ether_addr(addr))
err = dev_mc_add_excl(dev, addr);
return err;
}
static int macvlan_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr, u16 vid)
{
struct macvlan_dev *vlan = netdev_priv(dev);
int err = -EINVAL;
/* Support unicast filter only on passthru devices.
* Multicast filter should be allowed on all devices.
*/
if (!vlan->port->passthru && is_unicast_ether_addr(addr))
return -EOPNOTSUPP;
if (is_unicast_ether_addr(addr))
err = dev_uc_del(dev, addr);
else if (is_multicast_ether_addr(addr))
err = dev_mc_del(dev, addr);
return err;
}
static void macvlan_ethtool_get_drvinfo(struct net_device *dev,
struct ethtool_drvinfo *drvinfo)
{
strlcpy(drvinfo->driver, "macvlan", sizeof(drvinfo->driver));
strlcpy(drvinfo->version, "0.1", sizeof(drvinfo->version));
}
static int macvlan_ethtool_get_link_ksettings(struct net_device *dev,
struct ethtool_link_ksettings *cmd)
{
const struct macvlan_dev *vlan = netdev_priv(dev);
return __ethtool_get_link_ksettings(vlan->lowerdev, cmd);
}
static netdev_features_t macvlan_fix_features(struct net_device *dev,
netdev_features_t features)
{
struct macvlan_dev *vlan = netdev_priv(dev);
netdev_features_t lowerdev_features = vlan->lowerdev->features;
netdev_features_t mask;
features |= NETIF_F_ALL_FOR_ALL;
features &= (vlan->set_features | ~MACVLAN_FEATURES);
mask = features;
lowerdev_features &= (features | ~NETIF_F_LRO);
features = netdev_increment_features(lowerdev_features, features, mask);
macvlan: Add support for 'always_on' offload features Macvlan currently inherits all of its features from the lower device. When lower device disables offload support, this causes macvlan to disable offload support as well. This causes performance regression when using macvlan/macvtap in bridge mode. It can be easily demonstrated by creating 2 namespaces using macvlan in bridge mode and running netperf between them: MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 87380 16384 16384 20.00 1204.61 To restore the performance, we add software offload features to the list of "always_on" features for macvlan. This way when a namespace or a guest using macvtap initially sends a packet, this packet will not be segmented at macvlan level. It will only be segmented when macvlan sends the packet to the lower device. MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 87380 16384 16384 20.00 5507.35 Fixes: 6acf54f1cf0a6747bac9fea26f34cfc5a9029523 (macvtap: Add support of packet capture on macvtap device.) Fixes: 797f87f83b60685ff8a13fa0572d2f10393c50d3 (macvlan: fix netdev feature propagation from lower device) CC: Florian Westphal <fw@strlen.de> CC: Christian Borntraeger <borntraeger@de.ibm.com> CC: Jason Wang <jasowang@redhat.com> CC: Michael S. Tsirkin <mst@redhat.com> Tested-by: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-04 04:33:53 +08:00
features |= ALWAYS_ON_FEATURES;
features &= ~NETIF_F_NETNS_LOCAL;
return features;
}
#ifdef CONFIG_NET_POLL_CONTROLLER
static void macvlan_dev_poll_controller(struct net_device *dev)
{
return;
}
static int macvlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *real_dev = vlan->lowerdev;
struct netpoll *netpoll;
int err = 0;
netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL);
err = -ENOMEM;
if (!netpoll)
goto out;
err = __netpoll_setup(netpoll, real_dev);
if (err) {
kfree(netpoll);
goto out;
}
vlan->netpoll = netpoll;
out:
return err;
}
static void macvlan_dev_netpoll_cleanup(struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct netpoll *netpoll = vlan->netpoll;
if (!netpoll)
return;
vlan->netpoll = NULL;
__netpoll_free_async(netpoll);
}
#endif /* CONFIG_NET_POLL_CONTROLLER */
static int macvlan_dev_get_iflink(const struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
return vlan->lowerdev->ifindex;
}
static const struct ethtool_ops macvlan_ethtool_ops = {
.get_link = ethtool_op_get_link,
.get_link_ksettings = macvlan_ethtool_get_link_ksettings,
.get_drvinfo = macvlan_ethtool_get_drvinfo,
};
static const struct net_device_ops macvlan_netdev_ops = {
.ndo_init = macvlan_init,
.ndo_uninit = macvlan_uninit,
.ndo_open = macvlan_open,
.ndo_stop = macvlan_stop,
.ndo_start_xmit = macvlan_start_xmit,
.ndo_change_mtu = macvlan_change_mtu,
.ndo_fix_features = macvlan_fix_features,
.ndo_change_rx_flags = macvlan_change_rx_flags,
.ndo_set_mac_address = macvlan_set_mac_address,
.ndo_set_rx_mode = macvlan_set_mac_lists,
.ndo_get_stats64 = macvlan_dev_get_stats64,
.ndo_validate_addr = eth_validate_addr,
.ndo_vlan_rx_add_vid = macvlan_vlan_rx_add_vid,
.ndo_vlan_rx_kill_vid = macvlan_vlan_rx_kill_vid,
.ndo_fdb_add = macvlan_fdb_add,
.ndo_fdb_del = macvlan_fdb_del,
.ndo_fdb_dump = ndo_dflt_fdb_dump,
macvlan: Fix lockdep warnings with stacked macvlan devices Macvlan devices try to avoid stacking, but that's not always successfull or even desired. As an example, the following configuration is perefectly legal and valid: eth0 <--- macvlan0 <---- vlan0.10 <--- macvlan1 However, this configuration produces the following lockdep trace: [ 115.620418] ====================================================== [ 115.620477] [ INFO: possible circular locking dependency detected ] [ 115.620516] 3.15.0-rc1+ #24 Not tainted [ 115.620540] ------------------------------------------------------- [ 115.620577] ip/1704 is trying to acquire lock: [ 115.620604] (&vlan_netdev_addr_lock_key/1){+.....}, at: [<ffffffff815df49c>] dev_uc_sync+0x3c/0x80 [ 115.620686] but task is already holding lock: [ 115.620723] (&macvlan_netdev_addr_lock_key){+.....}, at: [<ffffffff815da5be>] dev_set_rx_mode+0x1e/0x40 [ 115.620795] which lock already depends on the new lock. [ 115.620853] the existing dependency chain (in reverse order) is: [ 115.620894] -> #1 (&macvlan_netdev_addr_lock_key){+.....}: [ 115.620935] [<ffffffff810d57f2>] lock_acquire+0xa2/0x130 [ 115.620974] [<ffffffff816f62e7>] _raw_spin_lock_nested+0x37/0x50 [ 115.621019] [<ffffffffa07296c3>] vlan_dev_set_rx_mode+0x53/0x110 [8021q] [ 115.621066] [<ffffffff815da557>] __dev_set_rx_mode+0x57/0xa0 [ 115.621105] [<ffffffff815da5c6>] dev_set_rx_mode+0x26/0x40 [ 115.621143] [<ffffffff815da6be>] __dev_open+0xde/0x140 [ 115.621174] [<ffffffff815da9ad>] __dev_change_flags+0x9d/0x170 [ 115.621174] [<ffffffff815daaa9>] dev_change_flags+0x29/0x60 [ 115.621174] [<ffffffff815e7f11>] do_setlink+0x321/0x9a0 [ 115.621174] [<ffffffff815ea59f>] rtnl_newlink+0x51f/0x730 [ 115.621174] [<ffffffff815e6e75>] rtnetlink_rcv_msg+0x95/0x250 [ 115.621174] [<ffffffff81608b19>] netlink_rcv_skb+0xa9/0xc0 [ 115.621174] [<ffffffff815e6dca>] rtnetlink_rcv+0x2a/0x40 [ 115.621174] [<ffffffff81608150>] netlink_unicast+0xf0/0x1c0 [ 115.621174] [<ffffffff8160851f>] netlink_sendmsg+0x2ff/0x740 [ 115.621174] [<ffffffff815bc9db>] sock_sendmsg+0x8b/0xc0 [ 115.621174] [<ffffffff815bd4b9>] ___sys_sendmsg+0x369/0x380 [ 115.621174] [<ffffffff815bdbb2>] __sys_sendmsg+0x42/0x80 [ 115.621174] [<ffffffff815bdc02>] SyS_sendmsg+0x12/0x20 [ 115.621174] [<ffffffff816ffd69>] system_call_fastpath+0x16/0x1b [ 115.621174] -> #0 (&vlan_netdev_addr_lock_key/1){+.....}: [ 115.621174] [<ffffffff810d4d43>] __lock_acquire+0x1773/0x1a60 [ 115.621174] [<ffffffff810d57f2>] lock_acquire+0xa2/0x130 [ 115.621174] [<ffffffff816f62e7>] _raw_spin_lock_nested+0x37/0x50 [ 115.621174] [<ffffffff815df49c>] dev_uc_sync+0x3c/0x80 [ 115.621174] [<ffffffffa0696d2a>] macvlan_set_mac_lists+0xca/0x110 [macvlan] [ 115.621174] [<ffffffff815da557>] __dev_set_rx_mode+0x57/0xa0 [ 115.621174] [<ffffffff815da5c6>] dev_set_rx_mode+0x26/0x40 [ 115.621174] [<ffffffff815da6be>] __dev_open+0xde/0x140 [ 115.621174] [<ffffffff815da9ad>] __dev_change_flags+0x9d/0x170 [ 115.621174] [<ffffffff815daaa9>] dev_change_flags+0x29/0x60 [ 115.621174] [<ffffffff815e7f11>] do_setlink+0x321/0x9a0 [ 115.621174] [<ffffffff815ea59f>] rtnl_newlink+0x51f/0x730 [ 115.621174] [<ffffffff815e6e75>] rtnetlink_rcv_msg+0x95/0x250 [ 115.621174] [<ffffffff81608b19>] netlink_rcv_skb+0xa9/0xc0 [ 115.621174] [<ffffffff815e6dca>] rtnetlink_rcv+0x2a/0x40 [ 115.621174] [<ffffffff81608150>] netlink_unicast+0xf0/0x1c0 [ 115.621174] [<ffffffff8160851f>] netlink_sendmsg+0x2ff/0x740 [ 115.621174] [<ffffffff815bc9db>] sock_sendmsg+0x8b/0xc0 [ 115.621174] [<ffffffff815bd4b9>] ___sys_sendmsg+0x369/0x380 [ 115.621174] [<ffffffff815bdbb2>] __sys_sendmsg+0x42/0x80 [ 115.621174] [<ffffffff815bdc02>] SyS_sendmsg+0x12/0x20 [ 115.621174] [<ffffffff816ffd69>] system_call_fastpath+0x16/0x1b [ 115.621174] other info that might help us debug this: [ 115.621174] Possible unsafe locking scenario: [ 115.621174] CPU0 CPU1 [ 115.621174] ---- ---- [ 115.621174] lock(&macvlan_netdev_addr_lock_key); [ 115.621174] lock(&vlan_netdev_addr_lock_key/1); [ 115.621174] lock(&macvlan_netdev_addr_lock_key); [ 115.621174] lock(&vlan_netdev_addr_lock_key/1); [ 115.621174] *** DEADLOCK *** [ 115.621174] 2 locks held by ip/1704: [ 115.621174] #0: (rtnl_mutex){+.+.+.}, at: [<ffffffff815e6dbb>] rtnetlink_rcv+0x1b/0x40 [ 115.621174] #1: (&macvlan_netdev_addr_lock_key){+.....}, at: [<ffffffff815da5be>] dev_set_rx_mode+0x1e/0x40 [ 115.621174] stack backtrace: [ 115.621174] CPU: 3 PID: 1704 Comm: ip Not tainted 3.15.0-rc1+ #24 [ 115.621174] Hardware name: Hewlett-Packard HP xw8400 Workstation/0A08h, BIOS 786D5 v02.38 10/25/2010 [ 115.621174] ffffffff82339ae0 ffff880465f79568 ffffffff816ee20c ffffffff82339ae0 [ 115.621174] ffff880465f795a8 ffffffff816e9e1b ffff880465f79600 ffff880465b019c8 [ 115.621174] 0000000000000001 0000000000000002 ffff880465b019c8 ffff880465b01230 [ 115.621174] Call Trace: [ 115.621174] [<ffffffff816ee20c>] dump_stack+0x4d/0x66 [ 115.621174] [<ffffffff816e9e1b>] print_circular_bug+0x200/0x20e [ 115.621174] [<ffffffff810d4d43>] __lock_acquire+0x1773/0x1a60 [ 115.621174] [<ffffffff810d3172>] ? trace_hardirqs_on_caller+0xb2/0x1d0 [ 115.621174] [<ffffffff810d57f2>] lock_acquire+0xa2/0x130 [ 115.621174] [<ffffffff815df49c>] ? dev_uc_sync+0x3c/0x80 [ 115.621174] [<ffffffff816f62e7>] _raw_spin_lock_nested+0x37/0x50 [ 115.621174] [<ffffffff815df49c>] ? dev_uc_sync+0x3c/0x80 [ 115.621174] [<ffffffff815df49c>] dev_uc_sync+0x3c/0x80 [ 115.621174] [<ffffffffa0696d2a>] macvlan_set_mac_lists+0xca/0x110 [macvlan] [ 115.621174] [<ffffffff815da557>] __dev_set_rx_mode+0x57/0xa0 [ 115.621174] [<ffffffff815da5c6>] dev_set_rx_mode+0x26/0x40 [ 115.621174] [<ffffffff815da6be>] __dev_open+0xde/0x140 [ 115.621174] [<ffffffff815da9ad>] __dev_change_flags+0x9d/0x170 [ 115.621174] [<ffffffff815daaa9>] dev_change_flags+0x29/0x60 [ 115.621174] [<ffffffff811e1db1>] ? mem_cgroup_bad_page_check+0x21/0x30 [ 115.621174] [<ffffffff815e7f11>] do_setlink+0x321/0x9a0 [ 115.621174] [<ffffffff810d394c>] ? __lock_acquire+0x37c/0x1a60 [ 115.621174] [<ffffffff815ea59f>] rtnl_newlink+0x51f/0x730 [ 115.621174] [<ffffffff815ea169>] ? rtnl_newlink+0xe9/0x730 [ 115.621174] [<ffffffff815e6e75>] rtnetlink_rcv_msg+0x95/0x250 [ 115.621174] [<ffffffff810d329d>] ? trace_hardirqs_on+0xd/0x10 [ 115.621174] [<ffffffff815e6dbb>] ? rtnetlink_rcv+0x1b/0x40 [ 115.621174] [<ffffffff815e6de0>] ? rtnetlink_rcv+0x40/0x40 [ 115.621174] [<ffffffff81608b19>] netlink_rcv_skb+0xa9/0xc0 [ 115.621174] [<ffffffff815e6dca>] rtnetlink_rcv+0x2a/0x40 [ 115.621174] [<ffffffff81608150>] netlink_unicast+0xf0/0x1c0 [ 115.621174] [<ffffffff8160851f>] netlink_sendmsg+0x2ff/0x740 [ 115.621174] [<ffffffff815bc9db>] sock_sendmsg+0x8b/0xc0 [ 115.621174] [<ffffffff8119d4af>] ? might_fault+0x5f/0xb0 [ 115.621174] [<ffffffff8119d4f8>] ? might_fault+0xa8/0xb0 [ 115.621174] [<ffffffff8119d4af>] ? might_fault+0x5f/0xb0 [ 115.621174] [<ffffffff815cb51e>] ? verify_iovec+0x5e/0xe0 [ 115.621174] [<ffffffff815bd4b9>] ___sys_sendmsg+0x369/0x380 [ 115.621174] [<ffffffff816faa0d>] ? __do_page_fault+0x11d/0x570 [ 115.621174] [<ffffffff810cfe9f>] ? up_read+0x1f/0x40 [ 115.621174] [<ffffffff816fab04>] ? __do_page_fault+0x214/0x570 [ 115.621174] [<ffffffff8120a10b>] ? mntput_no_expire+0x6b/0x1c0 [ 115.621174] [<ffffffff8120a0b7>] ? mntput_no_expire+0x17/0x1c0 [ 115.621174] [<ffffffff8120a284>] ? mntput+0x24/0x40 [ 115.621174] [<ffffffff815bdbb2>] __sys_sendmsg+0x42/0x80 [ 115.621174] [<ffffffff815bdc02>] SyS_sendmsg+0x12/0x20 [ 115.621174] [<ffffffff816ffd69>] system_call_fastpath+0x16/0x1b Fix this by correctly providing macvlan lockdep class. Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-17 05:04:56 +08:00
.ndo_get_lock_subclass = macvlan_get_nest_level,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = macvlan_dev_poll_controller,
.ndo_netpoll_setup = macvlan_dev_netpoll_setup,
.ndo_netpoll_cleanup = macvlan_dev_netpoll_cleanup,
#endif
.ndo_get_iflink = macvlan_dev_get_iflink,
.ndo_features_check = passthru_features_check,
};
macvtap: Limit packet queue length Mark Wagner reported OOM symptoms when sending UDP traffic over a macvtap link to a kvm receiver. This appears to be caused by the fact that macvtap packet queues are unlimited in length. This means that if the receiver can't keep up with the rate of flow, then we will hit OOM. Of course it gets worse if the OOM killer then decides to kill the receiver. This patch imposes a cap on the packet queue length, in the same way as the tuntap driver, using the device TX queue length. Please note that macvtap currently has no way of giving congestion notification, that means the software device TX queue cannot be used and packets will always be dropped once the macvtap driver queue fills up. This shouldn't be a great problem for the scenario where macvtap is used to feed a kvm receiver, as the traffic is most likely external in origin so congestion notification can't be applied anyway. Of course, if anybody decides to complain about guest-to-guest UDP packet loss down the track, then we may have to revisit this. Incidentally, this patch also fixes a real memory leak when macvtap_get_queue fails. Chris Wright noticed that for this patch to work, we need a non-zero TX queue length. This patch includes his work to change the default macvtap TX queue length to 500. Reported-by: Mark Wagner <mwagner@redhat.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Acked-by: Chris Wright <chrisw@sous-sol.org> Acked-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-07-22 05:44:31 +08:00
void macvlan_common_setup(struct net_device *dev)
{
ether_setup(dev);
net: use core MTU range checking in core net infra geneve: - Merge __geneve_change_mtu back into geneve_change_mtu, set max_mtu - This one isn't quite as straight-forward as others, could use some closer inspection and testing macvlan: - set min/max_mtu tun: - set min/max_mtu, remove tun_net_change_mtu vxlan: - Merge __vxlan_change_mtu back into vxlan_change_mtu - Set max_mtu to IP_MAX_MTU and retain dynamic MTU range checks in change_mtu function - This one is also not as straight-forward and could use closer inspection and testing from vxlan folks bridge: - set max_mtu of IP_MAX_MTU and retain dynamic MTU range checks in change_mtu function openvswitch: - set min/max_mtu, remove internal_dev_change_mtu - note: max_mtu wasn't checked previously, it's been set to 65535, which is the largest possible size supported sch_teql: - set min/max_mtu (note: max_mtu previously unchecked, used max of 65535) macsec: - min_mtu = 0, max_mtu = 65535 macvlan: - min_mtu = 0, max_mtu = 65535 ntb_netdev: - min_mtu = 0, max_mtu = 65535 veth: - min_mtu = 68, max_mtu = 65535 8021q: - min_mtu = 0, max_mtu = 65535 CC: netdev@vger.kernel.org CC: Nicolas Dichtel <nicolas.dichtel@6wind.com> CC: Hannes Frederic Sowa <hannes@stressinduktion.org> CC: Tom Herbert <tom@herbertland.com> CC: Daniel Borkmann <daniel@iogearbox.net> CC: Alexander Duyck <alexander.h.duyck@intel.com> CC: Paolo Abeni <pabeni@redhat.com> CC: Jiri Benc <jbenc@redhat.com> CC: WANG Cong <xiyou.wangcong@gmail.com> CC: Roopa Prabhu <roopa@cumulusnetworks.com> CC: Pravin B Shelar <pshelar@ovn.org> CC: Sabrina Dubroca <sd@queasysnail.net> CC: Patrick McHardy <kaber@trash.net> CC: Stephen Hemminger <stephen@networkplumber.org> CC: Pravin Shelar <pshelar@nicira.com> CC: Maxim Krasnyansky <maxk@qti.qualcomm.com> Signed-off-by: Jarod Wilson <jarod@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-21 01:55:20 +08:00
dev->min_mtu = 0;
dev->max_mtu = ETH_MAX_MTU;
dev->priv_flags &= ~IFF_TX_SKB_SHARING;
netif_keep_dst(dev);
dev->priv_flags |= IFF_UNICAST_FLT;
dev->netdev_ops = &macvlan_netdev_ops;
dev->destructor = free_netdev;
dev->header_ops = &macvlan_hard_header_ops;
dev->ethtool_ops = &macvlan_ethtool_ops;
macvtap: Limit packet queue length Mark Wagner reported OOM symptoms when sending UDP traffic over a macvtap link to a kvm receiver. This appears to be caused by the fact that macvtap packet queues are unlimited in length. This means that if the receiver can't keep up with the rate of flow, then we will hit OOM. Of course it gets worse if the OOM killer then decides to kill the receiver. This patch imposes a cap on the packet queue length, in the same way as the tuntap driver, using the device TX queue length. Please note that macvtap currently has no way of giving congestion notification, that means the software device TX queue cannot be used and packets will always be dropped once the macvtap driver queue fills up. This shouldn't be a great problem for the scenario where macvtap is used to feed a kvm receiver, as the traffic is most likely external in origin so congestion notification can't be applied anyway. Of course, if anybody decides to complain about guest-to-guest UDP packet loss down the track, then we may have to revisit this. Incidentally, this patch also fixes a real memory leak when macvtap_get_queue fails. Chris Wright noticed that for this patch to work, we need a non-zero TX queue length. This patch includes his work to change the default macvtap TX queue length to 500. Reported-by: Mark Wagner <mwagner@redhat.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Acked-by: Chris Wright <chrisw@sous-sol.org> Acked-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-07-22 05:44:31 +08:00
}
EXPORT_SYMBOL_GPL(macvlan_common_setup);
static void macvlan_setup(struct net_device *dev)
{
macvlan_common_setup(dev);
dev->priv_flags |= IFF_NO_QUEUE;
}
static int macvlan_port_create(struct net_device *dev)
{
struct macvlan_port *port;
unsigned int i;
int err;
if (dev->type != ARPHRD_ETHER || dev->flags & IFF_LOOPBACK)
return -EINVAL;
if (netdev_is_rx_handler_busy(dev))
return -EBUSY;
port = kzalloc(sizeof(*port), GFP_KERNEL);
if (port == NULL)
return -ENOMEM;
port->passthru = false;
port->dev = dev;
INIT_LIST_HEAD(&port->vlans);
for (i = 0; i < MACVLAN_HASH_SIZE; i++)
INIT_HLIST_HEAD(&port->vlan_hash[i]);
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
for (i = 0; i < MACVLAN_HASH_SIZE; i++)
INIT_HLIST_HEAD(&port->vlan_source_hash[i]);
skb_queue_head_init(&port->bc_queue);
INIT_WORK(&port->bc_work, macvlan_process_broadcast);
err = netdev_rx_handler_register(dev, macvlan_handle_frame, port);
if (err)
kfree(port);
else
dev->priv_flags |= IFF_MACVLAN_PORT;
return err;
}
static void macvlan_port_destroy(struct net_device *dev)
{
struct macvlan_port *port = macvlan_port_get_rtnl(dev);
struct sk_buff *skb;
dev->priv_flags &= ~IFF_MACVLAN_PORT;
netdev_rx_handler_unregister(dev);
/* After this point, no packet can schedule bc_work anymore,
* but we need to cancel it and purge left skbs if any.
*/
cancel_work_sync(&port->bc_work);
while ((skb = __skb_dequeue(&port->bc_queue))) {
const struct macvlan_dev *src = MACVLAN_SKB_CB(skb)->src;
if (src)
dev_put(src->dev);
kfree_skb(skb);
}
kfree(port);
}
static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[])
{
if (tb[IFLA_ADDRESS]) {
if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
return -EINVAL;
if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
return -EADDRNOTAVAIL;
}
if (data && data[IFLA_MACVLAN_FLAGS] &&
nla_get_u16(data[IFLA_MACVLAN_FLAGS]) & ~MACVLAN_FLAG_NOPROMISC)
return -EINVAL;
if (data && data[IFLA_MACVLAN_MODE]) {
switch (nla_get_u32(data[IFLA_MACVLAN_MODE])) {
case MACVLAN_MODE_PRIVATE:
case MACVLAN_MODE_VEPA:
case MACVLAN_MODE_BRIDGE:
case MACVLAN_MODE_PASSTHRU:
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
case MACVLAN_MODE_SOURCE:
break;
default:
return -EINVAL;
}
}
if (data && data[IFLA_MACVLAN_MACADDR_MODE]) {
switch (nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE])) {
case MACVLAN_MACADDR_ADD:
case MACVLAN_MACADDR_DEL:
case MACVLAN_MACADDR_FLUSH:
case MACVLAN_MACADDR_SET:
break;
default:
return -EINVAL;
}
}
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
if (data && data[IFLA_MACVLAN_MACADDR]) {
if (nla_len(data[IFLA_MACVLAN_MACADDR]) != ETH_ALEN)
return -EINVAL;
if (!is_valid_ether_addr(nla_data(data[IFLA_MACVLAN_MACADDR])))
return -EADDRNOTAVAIL;
}
if (data && data[IFLA_MACVLAN_MACADDR_COUNT])
return -EINVAL;
return 0;
}
/**
* reconfigure list of remote source mac address
* (only for macvlan devices in source mode)
* Note regarding alignment: all netlink data is aligned to 4 Byte, which
* suffices for both ether_addr_copy and ether_addr_equal_64bits usage.
*/
static int macvlan_changelink_sources(struct macvlan_dev *vlan, u32 mode,
struct nlattr *data[])
{
char *addr = NULL;
int ret, rem, len;
struct nlattr *nla, *head;
struct macvlan_source_entry *entry;
if (data[IFLA_MACVLAN_MACADDR])
addr = nla_data(data[IFLA_MACVLAN_MACADDR]);
if (mode == MACVLAN_MACADDR_ADD) {
if (!addr)
return -EINVAL;
return macvlan_hash_add_source(vlan, addr);
} else if (mode == MACVLAN_MACADDR_DEL) {
if (!addr)
return -EINVAL;
entry = macvlan_hash_lookup_source(vlan, addr);
if (entry) {
macvlan_hash_del_source(entry);
vlan->macaddr_count--;
}
} else if (mode == MACVLAN_MACADDR_FLUSH) {
macvlan_flush_sources(vlan->port, vlan);
} else if (mode == MACVLAN_MACADDR_SET) {
macvlan_flush_sources(vlan->port, vlan);
if (addr) {
ret = macvlan_hash_add_source(vlan, addr);
if (ret)
return ret;
}
if (!data || !data[IFLA_MACVLAN_MACADDR_DATA])
return 0;
head = nla_data(data[IFLA_MACVLAN_MACADDR_DATA]);
len = nla_len(data[IFLA_MACVLAN_MACADDR_DATA]);
nla_for_each_attr(nla, head, len, rem) {
if (nla_type(nla) != IFLA_MACVLAN_MACADDR ||
nla_len(nla) != ETH_ALEN)
continue;
addr = nla_data(nla);
ret = macvlan_hash_add_source(vlan, addr);
if (ret)
return ret;
}
} else {
return -EINVAL;
}
return 0;
}
int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct macvlan_port *port;
struct net_device *lowerdev;
int err;
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
int macmode;
bool create = false;
if (!tb[IFLA_LINK])
return -EINVAL;
lowerdev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
if (lowerdev == NULL)
return -ENODEV;
/* When creating macvlans or macvtaps on top of other macvlans - use
* the real device as the lowerdev.
*/
if (netif_is_macvlan(lowerdev))
lowerdev = macvlan_dev_real_dev(lowerdev);
if (!tb[IFLA_MTU])
dev->mtu = lowerdev->mtu;
else if (dev->mtu > lowerdev->mtu)
return -EINVAL;
net: use core MTU range checking in core net infra geneve: - Merge __geneve_change_mtu back into geneve_change_mtu, set max_mtu - This one isn't quite as straight-forward as others, could use some closer inspection and testing macvlan: - set min/max_mtu tun: - set min/max_mtu, remove tun_net_change_mtu vxlan: - Merge __vxlan_change_mtu back into vxlan_change_mtu - Set max_mtu to IP_MAX_MTU and retain dynamic MTU range checks in change_mtu function - This one is also not as straight-forward and could use closer inspection and testing from vxlan folks bridge: - set max_mtu of IP_MAX_MTU and retain dynamic MTU range checks in change_mtu function openvswitch: - set min/max_mtu, remove internal_dev_change_mtu - note: max_mtu wasn't checked previously, it's been set to 65535, which is the largest possible size supported sch_teql: - set min/max_mtu (note: max_mtu previously unchecked, used max of 65535) macsec: - min_mtu = 0, max_mtu = 65535 macvlan: - min_mtu = 0, max_mtu = 65535 ntb_netdev: - min_mtu = 0, max_mtu = 65535 veth: - min_mtu = 68, max_mtu = 65535 8021q: - min_mtu = 0, max_mtu = 65535 CC: netdev@vger.kernel.org CC: Nicolas Dichtel <nicolas.dichtel@6wind.com> CC: Hannes Frederic Sowa <hannes@stressinduktion.org> CC: Tom Herbert <tom@herbertland.com> CC: Daniel Borkmann <daniel@iogearbox.net> CC: Alexander Duyck <alexander.h.duyck@intel.com> CC: Paolo Abeni <pabeni@redhat.com> CC: Jiri Benc <jbenc@redhat.com> CC: WANG Cong <xiyou.wangcong@gmail.com> CC: Roopa Prabhu <roopa@cumulusnetworks.com> CC: Pravin B Shelar <pshelar@ovn.org> CC: Sabrina Dubroca <sd@queasysnail.net> CC: Patrick McHardy <kaber@trash.net> CC: Stephen Hemminger <stephen@networkplumber.org> CC: Pravin Shelar <pshelar@nicira.com> CC: Maxim Krasnyansky <maxk@qti.qualcomm.com> Signed-off-by: Jarod Wilson <jarod@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-21 01:55:20 +08:00
/* MTU range: 68 - lowerdev->max_mtu */
dev->min_mtu = ETH_MIN_MTU;
dev->max_mtu = lowerdev->max_mtu;
if (!tb[IFLA_ADDRESS])
eth_hw_addr_random(dev);
if (!macvlan_port_exists(lowerdev)) {
err = macvlan_port_create(lowerdev);
if (err < 0)
return err;
create = true;
}
port = macvlan_port_get_rtnl(lowerdev);
/* Only 1 macvlan device can be created in passthru mode */
if (port->passthru) {
/* The macvlan port must be not created this time,
* still goto destroy_macvlan_port for readability.
*/
err = -EINVAL;
goto destroy_macvlan_port;
}
vlan->lowerdev = lowerdev;
vlan->dev = dev;
vlan->port = port;
vlan->set_features = MACVLAN_FEATURES;
vlan->nest_level = dev_get_nest_level(lowerdev) + 1;
vlan->mode = MACVLAN_MODE_VEPA;
if (data && data[IFLA_MACVLAN_MODE])
vlan->mode = nla_get_u32(data[IFLA_MACVLAN_MODE]);
if (data && data[IFLA_MACVLAN_FLAGS])
vlan->flags = nla_get_u16(data[IFLA_MACVLAN_FLAGS]);
if (vlan->mode == MACVLAN_MODE_PASSTHRU) {
if (port->count) {
err = -EINVAL;
goto destroy_macvlan_port;
}
port->passthru = true;
eth_hw_addr_inherit(dev, lowerdev);
}
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
if (data && data[IFLA_MACVLAN_MACADDR_MODE]) {
if (vlan->mode != MACVLAN_MODE_SOURCE) {
err = -EINVAL;
goto destroy_macvlan_port;
}
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
macmode = nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE]);
err = macvlan_changelink_sources(vlan, macmode, data);
if (err)
goto destroy_macvlan_port;
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
}
err = register_netdevice(dev);
if (err < 0)
goto destroy_macvlan_port;
dev->priv_flags |= IFF_MACVLAN;
err = netdev_upper_dev_link(lowerdev, dev);
if (err)
goto unregister_netdev;
list_add_tail_rcu(&vlan->list, &port->vlans);
netif_stacked_transfer_operstate(lowerdev, dev);
macvlan: make operstate and carrier more accurate Currently when a macvlan is being initialized and the lower device is netif_carrier_ok(), the macvlan device doesn't run through rfc2863_policy() and is left with UNKNOWN operstate. Fix it by adding an unconditional linkwatch event for the new macvlan device. Similar fix is already used by the 8021q device (see register_vlan_dev()). Also fix the inconsistent state when the lower device has been down and its carrier was changed (when a device is down NETDEV_CHANGE doesn't get generated). The second issue can be seen f.e. when we have a macvlan on top of a 8021q device which has been down and its real device has been changing carrier states, after setting the 8021q device up, the macvlan device will have the same carrier state as it was before even though the 8021q can now have a different state. Example for case 1: 4: eth2: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP mode DEFAULT group default qlen 1000 $ ip l add l eth2 macvl0 type macvlan $ ip l set macvl0 up $ ip l sh macvl0 72: macvl0@eth2: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN mode DEFAULT group default link/ether f6:0b:54:0a:9d:a3 brd ff:ff:ff:ff:ff:ff Example for case 2 (order is important): Prestate: eth2 UP/CARRIER, vlan1 down, vlan1-macvlan down $ ip l set vlan1-macvlan up $ ip l sh vlan1-macvlan 71: vlan1-macvlan@vlan1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN mode DEFAULT group default link/ether 4a:b8:44:56:b9:b9 brd ff:ff:ff:ff:ff:ff [ eth2 loses CARRIER before vlan1 has been UP-ed ] $ ip l sh eth2 4: eth2: <NO-CARRIER,BROADCAST,MULTICAST,UP> mtu 1500 qdisc pfifo_fast state DOWN mode DEFAULT group default qlen 1000 link/ether 52:54:00:bf:57:16 brd ff:ff:ff:ff:ff:ff $ ip l sh vlan1-macvlan 71: vlan1-macvlan@vlan1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN mode DEFAULT group default link/ether 4a:b8:44:56:b9:b9 brd ff:ff:ff:ff:ff:ff $ ip l set vlan1 up $ ip l sh vlan1 70: vlan1@eth2: <NO-CARRIER,BROADCAST,MULTICAST,UP> mtu 1500 qdisc noqueue state LOWERLAYERDOWN mode DEFAULT group default qlen 1000 link/ether 52:54:00:bf:57:16 brd ff:ff:ff:ff:ff:ff $ ip l sh vlan1-macvlan 71: vlan1-macvlan@vlan1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN mode DEFAULT group default link/ether 4a:b8:44:56:b9:b9 brd ff:ff:ff:ff:ff:ff vlan1-macvlan is still UP, still has carrier and is still in the same operstate as before. After the patch in case 1 macvl0 has state UP as it should and in case 2 vlan1-macvlan has state LOWERLAYERDOWN again as it should. Note that while the lower macvlan device is down their carrier and thus operstate can go out of sync but that will be fixed once the lower device goes up again. This behaviour seems to have been present since beginning of git history. Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-28 00:50:43 +08:00
linkwatch_fire_event(dev);
return 0;
unregister_netdev:
unregister_netdevice(dev);
destroy_macvlan_port:
if (create)
macvlan_port_destroy(port->dev);
return err;
}
EXPORT_SYMBOL_GPL(macvlan_common_newlink);
static int macvlan_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
{
return macvlan_common_newlink(src_net, dev, tb, data);
}
void macvlan_dellink(struct net_device *dev, struct list_head *head)
{
struct macvlan_dev *vlan = netdev_priv(dev);
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
if (vlan->mode == MACVLAN_MODE_SOURCE)
macvlan_flush_sources(vlan->port, vlan);
list_del_rcu(&vlan->list);
unregister_netdevice_queue(dev, head);
netdev_upper_dev_unlink(vlan->lowerdev, dev);
}
EXPORT_SYMBOL_GPL(macvlan_dellink);
static int macvlan_changelink(struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
{
struct macvlan_dev *vlan = netdev_priv(dev);
enum macvlan_mode mode;
bool set_mode = false;
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
enum macvlan_macaddr_mode macmode;
int ret;
/* Validate mode, but don't set yet: setting flags may fail. */
if (data && data[IFLA_MACVLAN_MODE]) {
set_mode = true;
mode = nla_get_u32(data[IFLA_MACVLAN_MODE]);
/* Passthrough mode can't be set or cleared dynamically */
if ((mode == MACVLAN_MODE_PASSTHRU) !=
(vlan->mode == MACVLAN_MODE_PASSTHRU))
return -EINVAL;
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
if (vlan->mode == MACVLAN_MODE_SOURCE &&
vlan->mode != mode)
macvlan_flush_sources(vlan->port, vlan);
}
if (data && data[IFLA_MACVLAN_FLAGS]) {
__u16 flags = nla_get_u16(data[IFLA_MACVLAN_FLAGS]);
bool promisc = (flags ^ vlan->flags) & MACVLAN_FLAG_NOPROMISC;
if (vlan->port->passthru && promisc) {
int err;
if (flags & MACVLAN_FLAG_NOPROMISC)
err = dev_set_promiscuity(vlan->lowerdev, -1);
else
err = dev_set_promiscuity(vlan->lowerdev, 1);
if (err < 0)
return err;
}
vlan->flags = flags;
}
if (set_mode)
vlan->mode = mode;
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
if (data && data[IFLA_MACVLAN_MACADDR_MODE]) {
if (vlan->mode != MACVLAN_MODE_SOURCE)
return -EINVAL;
macmode = nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE]);
ret = macvlan_changelink_sources(vlan, macmode, data);
if (ret)
return ret;
}
return 0;
}
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
static size_t macvlan_get_size_mac(const struct macvlan_dev *vlan)
{
if (vlan->macaddr_count == 0)
return 0;
return nla_total_size(0) /* IFLA_MACVLAN_MACADDR_DATA */
+ vlan->macaddr_count * nla_total_size(sizeof(u8) * ETH_ALEN);
}
static size_t macvlan_get_size(const struct net_device *dev)
{
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
struct macvlan_dev *vlan = netdev_priv(dev);
return (0
+ nla_total_size(4) /* IFLA_MACVLAN_MODE */
+ nla_total_size(2) /* IFLA_MACVLAN_FLAGS */
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
+ nla_total_size(4) /* IFLA_MACVLAN_MACADDR_COUNT */
+ macvlan_get_size_mac(vlan) /* IFLA_MACVLAN_MACADDR */
);
}
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
static int macvlan_fill_info_macaddr(struct sk_buff *skb,
const struct macvlan_dev *vlan,
const int i)
{
struct hlist_head *h = &vlan->port->vlan_source_hash[i];
struct macvlan_source_entry *entry;
hlist_for_each_entry_rcu(entry, h, hlist) {
if (entry->vlan != vlan)
continue;
if (nla_put(skb, IFLA_MACVLAN_MACADDR, ETH_ALEN, entry->addr))
return 1;
}
return 0;
}
static int macvlan_fill_info(struct sk_buff *skb,
const struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
int i;
struct nlattr *nest;
if (nla_put_u32(skb, IFLA_MACVLAN_MODE, vlan->mode))
goto nla_put_failure;
if (nla_put_u16(skb, IFLA_MACVLAN_FLAGS, vlan->flags))
goto nla_put_failure;
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
if (nla_put_u32(skb, IFLA_MACVLAN_MACADDR_COUNT, vlan->macaddr_count))
goto nla_put_failure;
if (vlan->macaddr_count > 0) {
nest = nla_nest_start(skb, IFLA_MACVLAN_MACADDR_DATA);
if (nest == NULL)
goto nla_put_failure;
for (i = 0; i < MACVLAN_HASH_SIZE; i++) {
if (macvlan_fill_info_macaddr(skb, vlan, i))
goto nla_put_failure;
}
nla_nest_end(skb, nest);
}
return 0;
nla_put_failure:
return -EMSGSIZE;
}
static const struct nla_policy macvlan_policy[IFLA_MACVLAN_MAX + 1] = {
[IFLA_MACVLAN_MODE] = { .type = NLA_U32 },
[IFLA_MACVLAN_FLAGS] = { .type = NLA_U16 },
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 22:31:08 +08:00
[IFLA_MACVLAN_MACADDR_MODE] = { .type = NLA_U32 },
[IFLA_MACVLAN_MACADDR] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
[IFLA_MACVLAN_MACADDR_DATA] = { .type = NLA_NESTED },
[IFLA_MACVLAN_MACADDR_COUNT] = { .type = NLA_U32 },
};
int macvlan_link_register(struct rtnl_link_ops *ops)
{
/* common fields */
ops->validate = macvlan_validate;
ops->maxtype = IFLA_MACVLAN_MAX;
ops->policy = macvlan_policy;
ops->changelink = macvlan_changelink;
ops->get_size = macvlan_get_size;
ops->fill_info = macvlan_fill_info;
return rtnl_link_register(ops);
};
EXPORT_SYMBOL_GPL(macvlan_link_register);
static struct net *macvlan_get_link_net(const struct net_device *dev)
{
return dev_net(macvlan_dev_real_dev(dev));
}
static struct rtnl_link_ops macvlan_link_ops = {
.kind = "macvlan",
macvtap: Limit packet queue length Mark Wagner reported OOM symptoms when sending UDP traffic over a macvtap link to a kvm receiver. This appears to be caused by the fact that macvtap packet queues are unlimited in length. This means that if the receiver can't keep up with the rate of flow, then we will hit OOM. Of course it gets worse if the OOM killer then decides to kill the receiver. This patch imposes a cap on the packet queue length, in the same way as the tuntap driver, using the device TX queue length. Please note that macvtap currently has no way of giving congestion notification, that means the software device TX queue cannot be used and packets will always be dropped once the macvtap driver queue fills up. This shouldn't be a great problem for the scenario where macvtap is used to feed a kvm receiver, as the traffic is most likely external in origin so congestion notification can't be applied anyway. Of course, if anybody decides to complain about guest-to-guest UDP packet loss down the track, then we may have to revisit this. Incidentally, this patch also fixes a real memory leak when macvtap_get_queue fails. Chris Wright noticed that for this patch to work, we need a non-zero TX queue length. This patch includes his work to change the default macvtap TX queue length to 500. Reported-by: Mark Wagner <mwagner@redhat.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Acked-by: Chris Wright <chrisw@sous-sol.org> Acked-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-07-22 05:44:31 +08:00
.setup = macvlan_setup,
.newlink = macvlan_newlink,
.dellink = macvlan_dellink,
.get_link_net = macvlan_get_link_net,
.priv_size = sizeof(struct macvlan_dev),
};
static int macvlan_device_event(struct notifier_block *unused,
unsigned long event, void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct macvlan_dev *vlan, *next;
struct macvlan_port *port;
LIST_HEAD(list_kill);
if (!macvlan_port_exists(dev))
return NOTIFY_DONE;
port = macvlan_port_get_rtnl(dev);
switch (event) {
macvlan: make operstate and carrier more accurate Currently when a macvlan is being initialized and the lower device is netif_carrier_ok(), the macvlan device doesn't run through rfc2863_policy() and is left with UNKNOWN operstate. Fix it by adding an unconditional linkwatch event for the new macvlan device. Similar fix is already used by the 8021q device (see register_vlan_dev()). Also fix the inconsistent state when the lower device has been down and its carrier was changed (when a device is down NETDEV_CHANGE doesn't get generated). The second issue can be seen f.e. when we have a macvlan on top of a 8021q device which has been down and its real device has been changing carrier states, after setting the 8021q device up, the macvlan device will have the same carrier state as it was before even though the 8021q can now have a different state. Example for case 1: 4: eth2: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP mode DEFAULT group default qlen 1000 $ ip l add l eth2 macvl0 type macvlan $ ip l set macvl0 up $ ip l sh macvl0 72: macvl0@eth2: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN mode DEFAULT group default link/ether f6:0b:54:0a:9d:a3 brd ff:ff:ff:ff:ff:ff Example for case 2 (order is important): Prestate: eth2 UP/CARRIER, vlan1 down, vlan1-macvlan down $ ip l set vlan1-macvlan up $ ip l sh vlan1-macvlan 71: vlan1-macvlan@vlan1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN mode DEFAULT group default link/ether 4a:b8:44:56:b9:b9 brd ff:ff:ff:ff:ff:ff [ eth2 loses CARRIER before vlan1 has been UP-ed ] $ ip l sh eth2 4: eth2: <NO-CARRIER,BROADCAST,MULTICAST,UP> mtu 1500 qdisc pfifo_fast state DOWN mode DEFAULT group default qlen 1000 link/ether 52:54:00:bf:57:16 brd ff:ff:ff:ff:ff:ff $ ip l sh vlan1-macvlan 71: vlan1-macvlan@vlan1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN mode DEFAULT group default link/ether 4a:b8:44:56:b9:b9 brd ff:ff:ff:ff:ff:ff $ ip l set vlan1 up $ ip l sh vlan1 70: vlan1@eth2: <NO-CARRIER,BROADCAST,MULTICAST,UP> mtu 1500 qdisc noqueue state LOWERLAYERDOWN mode DEFAULT group default qlen 1000 link/ether 52:54:00:bf:57:16 brd ff:ff:ff:ff:ff:ff $ ip l sh vlan1-macvlan 71: vlan1-macvlan@vlan1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN mode DEFAULT group default link/ether 4a:b8:44:56:b9:b9 brd ff:ff:ff:ff:ff:ff vlan1-macvlan is still UP, still has carrier and is still in the same operstate as before. After the patch in case 1 macvl0 has state UP as it should and in case 2 vlan1-macvlan has state LOWERLAYERDOWN again as it should. Note that while the lower macvlan device is down their carrier and thus operstate can go out of sync but that will be fixed once the lower device goes up again. This behaviour seems to have been present since beginning of git history. Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-28 00:50:43 +08:00
case NETDEV_UP:
case NETDEV_CHANGE:
list_for_each_entry(vlan, &port->vlans, list)
netif_stacked_transfer_operstate(vlan->lowerdev,
vlan->dev);
break;
case NETDEV_FEAT_CHANGE:
list_for_each_entry(vlan, &port->vlans, list) {
vlan->dev->gso_max_size = dev->gso_max_size;
vlan->dev->gso_max_segs = dev->gso_max_segs;
netdev_update_features(vlan->dev);
}
break;
case NETDEV_CHANGEMTU:
list_for_each_entry(vlan, &port->vlans, list) {
if (vlan->dev->mtu <= dev->mtu)
continue;
dev_set_mtu(vlan->dev, dev->mtu);
}
break;
case NETDEV_CHANGEADDR:
if (!port->passthru)
return NOTIFY_DONE;
vlan = list_first_entry_or_null(&port->vlans,
struct macvlan_dev,
list);
if (macvlan_sync_address(vlan->dev, dev->dev_addr))
return NOTIFY_BAD;
break;
case NETDEV_UNREGISTER:
/* twiddle thumbs on netns device moves */
if (dev->reg_state != NETREG_UNREGISTERING)
break;
list_for_each_entry_safe(vlan, next, &port->vlans, list)
vlan->dev->rtnl_link_ops->dellink(vlan->dev, &list_kill);
unregister_netdevice_many(&list_kill);
break;
case NETDEV_PRE_TYPE_CHANGE:
/* Forbid underlaying device to change its type. */
return NOTIFY_BAD;
case NETDEV_NOTIFY_PEERS:
case NETDEV_BONDING_FAILOVER:
case NETDEV_RESEND_IGMP:
/* Propagate to all vlans */
list_for_each_entry(vlan, &port->vlans, list)
call_netdevice_notifiers(event, vlan->dev);
}
return NOTIFY_DONE;
}
static struct notifier_block macvlan_notifier_block __read_mostly = {
.notifier_call = macvlan_device_event,
};
static int __init macvlan_init_module(void)
{
int err;
register_netdevice_notifier(&macvlan_notifier_block);
err = macvlan_link_register(&macvlan_link_ops);
if (err < 0)
goto err1;
return 0;
err1:
unregister_netdevice_notifier(&macvlan_notifier_block);
return err;
}
static void __exit macvlan_cleanup_module(void)
{
rtnl_link_unregister(&macvlan_link_ops);
unregister_netdevice_notifier(&macvlan_notifier_block);
}
module_init(macvlan_init_module);
module_exit(macvlan_cleanup_module);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
MODULE_DESCRIPTION("Driver for MAC address based VLANs");
MODULE_ALIAS_RTNL_LINK("macvlan");